Descriptor: "Computer Science::Computer Vision and Pattern Recognition" / Publisher: hal ccsd - Searchworks@Jio Institute Digital Library Search Results

Your search keyword '"Computer Science::Computer Vision and Pattern Recognition"' showing total 1,888 results

Start Over Descriptor "Computer Science::Computer Vision and Pattern Recognition" Publisher hal ccsd

1,888 results on '"Computer Science::Computer Vision and Pattern Recognition"'

1. ConTesse: Accurate Occluding Contours for Subdivision Surfaces

Author: Chenxi Liu, Pierre Bénard, Aaron Hertzmann, Shayan Hoshyari, University of British Columbia (UBC), Melting the frontiers between Light, Shape and Matter (MANAO), Laboratoire Bordelais de Recherche en Informatique (LaBRI), Université de Bordeaux (UB)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Centre National de la Recherche Scientifique (CNRS)-Université de Bordeaux (UB)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Centre National de la Recherche Scientifique (CNRS)-Inria Bordeaux - Sud-Ouest, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Photonique, Numérique et Nanosciences (LP2N), Université de Bordeaux (UB)-Institut d'Optique Graduate School (IOGS)-Centre National de la Recherche Scientifique (CNRS)-Institut d'Optique Graduate School (IOGS)-Centre National de la Recherche Scientifique (CNRS), Adobe Research, and ANR-20-CE33-0002,MoStyle,Stylisation du mouvement pour l'animation 2D(2020)
Subjects: Computational Geometry (cs.CG), FOS: Computer and information sciences, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Geometry processing, Occluding Contours, Computer Graphics and Computer-Aided Design, Graphics (cs.GR), [INFO.INFO-GR]Computer Science [cs]/Graphics [cs.GR], Non-photorealistic rendering, Computer Science - Graphics, Computer Science::Graphics, Computer Science::Computer Vision and Pattern Recognition, Computer Science - Computational Geometry, ComputingMethodologies_COMPUTERGRAPHICS
Abstract: This paper proposes a method for computing the visible occluding contours of subdivision surfaces. The paper first introduces new theory for contour visibility of smooth surfaces. Necessary and sufficient conditions are introduced for when a sampled occluding contour is valid, that is, when it may be assigned consistent visibility. Previous methods do not guarantee these conditions, which helps explain why smooth contour visibility has been such a challenging problem in the past. The paper then proposes an algorithm that, given a subdivision surface, finds sampled contours satisfying these conditions, and then generates a new triangle mesh matching the given occluding contours. The contours of the output triangle mesh may then be rendered with standard non-photorealistic rendering algorithms, using the mesh for visibility computation. The method can be applied to any triangle mesh, by treating it as the base mesh of a subdivision surface., Accepted to ACM Transactions on Graphics (TOG)
Published: 2023

2. PnP-ReG: Learned Regularizing Gradient for Plug-and-Play Gradient Descent

Author: Rita Fermanian, Mikael Le Pendu, Christine Guillemot, Analysis representation, compression and communication of visual data (Sirocco), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAL, IMAGE ET LANGAGE (IRISA-D6), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), and ANR-19-CHIA-0007,DeepCIM,Apprentissage profond pour imagerie computationnelle avec nouvelles modalités d'images(2019)
Subjects: FOS: Computer and information sciences, Inverse problems, Plug-and-Play Prior, Computer Science - Machine Learning, 62H35, 68U10, 94A08, 68T99, Gradient Descent MSC codes. 62H35, Applied Mathematics, General Mathematics, Computer Vision and Pattern Recognition (cs.CV), Image and Video Processing (eess.IV), Computer Science - Computer Vision and Pattern Recognition, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 68U10, 68T99, Electrical Engineering and Systems Science - Image and Video Processing, Machine Learning (cs.LG), 94A08, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Computer Science::Computer Vision and Pattern Recognition, Regularization, FOS: Electrical engineering, electronic engineering, information engineering
Abstract: The Plug-and-Play (PnP) framework makes it possible to integrate advanced image denoising priors into optimization algorithms, to efficiently solve a variety of image restoration tasks generally formulated as Maximum A Posteriori (MAP) estimation problems. The Plug-and-Play alternating direction method of multipliers (ADMM) and the Regularization by Denoising (RED) algorithms are two examples of such methods that made a breakthrough in image restoration. However, while the former method only applies to proximal algorithms, it has recently been shown that there exists no regularization that explains the RED algorithm when the denoisers lack Jacobian symmetry, which happen to be the case of most practical denoisers. To the best of our knowledge, there exists no method for training a network that directly represents the gradient of a regularizer, which can be directly used in Plug-and-Play gradient-based algorithms. We show that it is possible to train a network directly modeling the gradient of a MAP regularizer while jointly training the corresponding MAP denoiser. We use this network in gradient-based optimization methods and obtain better results comparing to other generic Plug-and-Play approaches. We also show that the regularizer can be used as a pre-trained network for unrolled gradient descent. Lastly, we show that the resulting denoiser allows for a better convergence of the Plug-and-Play ADMM.
Published: 2022

3. Fast reconstruction of hyperspectral images from coded acquisitions using a separability assumption

Author: Elizabeth Hemsley, Ibrahim Ardi, Tony Rouvier, Simon Lacroix, Hervé Carfantan, Antoine Monmayrant, Équipe Photonique (LAAS-PHOTO), Laboratoire d'analyse et d'architecture des systèmes (LAAS), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT), Institut de recherche en astrophysique et planétologie (IRAP), Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire Midi-Pyrénées (OMP), Institut de Recherche pour le Développement (IRD)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Institut de Recherche pour le Développement (IRD)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Centre National de la Recherche Scientifique (CNRS), Équipe Robotique et InteractionS (LAAS-RIS), ANR-18-ASTR-0012,ImHypAd,Imageur Hyperspectral Adaptatif(2018), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire Midi-Pyrénées (OMP), and Institut de Recherche pour le Développement (IRD)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Université Fédérale Toulouse Midi-Pyrénées-Météo-France -Institut de Recherche pour le Développement (IRD)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Centre National de la Recherche Scientifique (CNRS)
Subjects: [SPI.ELEC]Engineering Sciences [physics]/Electromagnetism, Computer Science::Computer Vision and Pattern Recognition, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [SPI.OPTI]Engineering Sciences [physics]/Optics / Photonic, [SPI.NANO]Engineering Sciences [physics]/Micro and nanotechnologies/Microelectronics, Atomic and Molecular Physics, and Optics
Abstract: We present a fast reconstruction algorithm for hyperspectral images, utilizing a small amount of data without the need for any training. The method is implemented with a dual disperser hyperspectral imager and makes use of spatial-spectral correlations by a so-called separability assumption that assumes that the image is made of regions of homogenous spectra. The reconstruction algorithm is simple and ready-to-use and does not require any prior knowledge of the scene. A simple proof-of-principle experiment is performed, demonstrating that only a small number of acquisitions are required, and the resulting compressed data-cube is reconstructed near instantaneously.
Published: 2022

4. A Novel Image Denoising Algorithm Using Concepts of Quantum Many-Body Theory

Author: Sayantan Dutta, Adrian Basarab, Bertrand Georgeot, Denis Kouamé, CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Toulouse Mind & Brain Institut (TMBI), Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT), Laboratoire de Physique Théorique (LPT), Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Fédération de recherche « Matière et interactions » (FeRMI), Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS), Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Institut de Recherche sur les Systèmes Atomiques et Moléculaires Complexes (IRSAMC), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université Claude Bernard Lyon 1 (UCBL), and Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)
Subjects: FOS: Computer and information sciences, History, Polymers and Plastics, Computer Vision and Pattern Recognition (cs.CV), Image and Video Processing (eess.IV), Computer Science - Computer Vision and Pattern Recognition, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Electrical Engineering and Systems Science - Image and Video Processing, Industrial and Manufacturing Engineering, [PHYS.QPHY]Physics [physics]/Quantum Physics [quant-ph], Control and Systems Engineering, Computer Science::Computer Vision and Pattern Recognition, Signal Processing, FOS: Electrical engineering, electronic engineering, information engineering, [INFO]Computer Science [cs], Computer Vision and Pattern Recognition, Electrical and Electronic Engineering, Business and International Management, Software
Abstract: Sparse representation of real-life images is a very effective approach in imaging applications, such as denoising. In recent years, with the growth of computing power, data-driven strategies exploiting the redundancy within patches extracted from one or several images to increase sparsity have become more prominent. This paper presents a novel image denoising algorithm exploiting such an image-dependent basis inspired by the quantum many-body theory. Based on patch analysis, the similarity measures in a local image neighborhood are formalized through a term akin to interaction in quantum mechanics that can efficiently preserve the local structures of real images. The versatile nature of this adaptive basis extends the scope of its application to image-independent or image-dependent noise scenarios without any adjustment. We carry out a rigorous comparison with contemporary methods to demonstrate the denoising capability of the proposed algorithm regardless of the image characteristics, noise statistics and intensity. We illustrate the properties of the hyperparameters and their respective effects on the denoising performance, together with automated rules of selecting their values close to the optimal one in experimental setups with ground truth not available. Finally, we show the ability of our approach to deal with practical images denoising problems such as medical ultrasound image despeckling applications., 24 pages, 14 figures; complements and expands arXiv:2108.13778
Published: 2022

5. Deep-Blur : Blind Identification and Deblurring with Convolutional Neural Networks

Author: Debarnot, Valentin, Weiss, Pierre, Department of Computer Science (University of Basel), University of Basel (Unibas), Centre National de la Recherche Scientifique (CNRS), Institut de Mathématiques de Toulouse UMR5219 (IMT), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), and Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)
Subjects: Blind inverse problems, Spatially variant blur, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Blind deblurring, Computer Science::Computer Vision and Pattern Recognition, Unrolled network, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Deep learning, Identification network
Abstract: We propose a neural network architecture and a training procedure to estimate blurring operators and deblur images from a single degraded image. The key assumption is that the forward operators can be parameterized by a lowdimensional vector. The considered models include a description of the point spread function with Zernike polynomials in the pupil plane or product-convolution expansions, which allow to tackle space varying operators. Numerical experiments reveal that the proposed method recovers the blur parameters robustly even for large noise levels. This estimate can then used as an input of an unrolled neural network to deblur the image. It is trained with a specific sampling procedure adapted to a family of parameterized operators. This strategy provides a fast and accurate blind inverse problem solver, requiring nearly no human interaction once the operator parameterization has been set up. It adapts to arbirtrary noise levels and considerably improves alternative blind deblurring softwares in the examples considered in this paper, especially in the high noise regimes. 1
Published: 2022

6. Generalized Rectifier Wavelet Covariance Models For Texture Synthesis

Author: Brochard, Antoine, Zhang, Sixin, Mallat, Stéphane, Dynamics of Geometric Networks (DYOGENE), Département d'informatique - ENS Paris (DI-ENS), École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS)-Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria), Algorithmes Parallèles et Optimisation (IRIT-APO), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Toulouse Mind & Brain Institut (TMBI), Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT), Université Paris sciences et lettres (PSL), ANR-19-P3IA-0001,PRAIRIE,PaRis Artificial Intelligence Research InstitutE(2019), and ANR-19-PI3A-0004,Future - PI3A
Subjects: Signal Processing (eess.SP), FOS: Computer and information sciences, Computer Science - Machine Learning, Computer Vision and Pattern Recognition (cs.CV), Image and Video Processing (eess.IV), Computer Science - Computer Vision and Pattern Recognition, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Generative models, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Machine Learning (stat.ML), Electrical Engineering and Systems Science - Image and Video Processing, Texture synthesis, Wavelets, Machine Learning (cs.LG), Statistics - Machine Learning, Computer Science::Computer Vision and Pattern Recognition, FOS: Electrical engineering, electronic engineering, information engineering, Electrical Engineering and Systems Science - Signal Processing
Abstract: State-of-the-art maximum entropy models for texture synthesis are built from statistics relying on image representations defined by convolutional neural networks (CNN). Such representations capture rich structures in texture images, outperforming wavelet-based representations in this regard. However, conversely to neural networks, wavelets offer meaningful representations, as they are known to detect structures at multiple scales (e.g. edges) in images. In this work, we propose a family of statistics built upon non-linear wavelet based representations, that can be viewed as a particular instance of a one-layer CNN, using a generalized rectifier non-linearity. These statistics significantly improve the visual quality of previous classical wavelet-based models, and allow one to produce syntheses of similar quality to state-of-the-art models, on both gray-scale and color textures., Comment: To be published as a conference paper at the International Conference on Learning Representations (ICLR) 2022
Published: 2022

7. Oscillatory Neural Network as Hetero-Associative Memory for Image Edge Detection

Author: Madeleine Abernot, Thierry Gil, Aida Todri-Sanial, Smart Integrated Electronic Systems (SmartIES), Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier (LIRMM), Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM), Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM), and European Project: 871501,H2020-EU.2.1.1. - INDUSTRIAL LEADERSHIP - Leadership in enabling and industrial technologies - Information and Communication Technologies (ICT),H2020-ICT-2019-2,NeurONN(2020)
Subjects: FOS: Computer and information sciences, Neuromorphic Computing, Computer Science - Artificial Intelligence, Image and Video Processing (eess.IV), ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Computer Science - Neural and Evolutionary Computing, Electrical Engineering and Systems Science - Image and Video Processing, [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Artificial Intelligence (cs.AI), Oscillatory Neural Networks, Computer Science::Computer Vision and Pattern Recognition, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], FOS: Electrical engineering, electronic engineering, information engineering, Neural and Evolutionary Computing (cs.NE), Edge detection, Hetero-Associative Memory
Abstract: International audience; The increasing amount of data to be processed on edge devices, such as cameras, has motivated Artificial Intelligence (AI) integration at the edge. Typical image processing methods performed at the edge, such as feature extraction or edge detection, use convolutional filters that are energy, computation, and memory hungry algorithms. But edge devices and cameras have scarce computational resources, bandwidth, and power and are limited due to privacy constraints to send data over to the cloud. Thus, there is a need to process image data at the edge. Over the years, this need has incited a lot of interest in implementing neuromorphic computing at the edge. Neuromorphic systems aim to emulate the biological neural functions to achieve energy-efficient computing. Recently, Oscillatory Neural Networks (ONN) present a novel brain-inspired computing approach by emulating brain oscillations to perform autoassociative memory types of applications. To speed up image edge detection and reduce its power consumption, we perform an in-depth investigation with ONNs. We propose a novel image processing method by using ONNs as a hetero-associative memory (HAM) for image edge detection. We simulate our ONN-HAM solution using first, a Matlab emulator, and then a fully digital ONN design. We show results on gray scale square evaluation maps, also on black and white and gray scale 28x28 MNIST images and finally on black and white 512x512 standard test images. We compare our solution with standard edge detection filters such as Sobel and Canny. Finally, using the fully digital design simulation results, we report on timing and resource characteristics, and evaluate its feasibility for real-time image processing applications. Our digital ONN-HAM solution can process images with up to 120x120 pixels (166 MHz system frequency) respecting real-time camera constraints. This work is the first to explore ONNs as hetero-associative memory for image processing applications.
Published: 2022

8. A hybrid approach combining cnns and variational modelling for blind image denoising

Author: Rekik Dit Nekhili, Rim, Descombes, Xavier, Calatroni, Luca, Capture and Analysis of Shapes in Motion (MORPHEO), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK), Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP ), Université Grenoble Alpes (UGA)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP ), Université Grenoble Alpes (UGA), Morphologie et Images (MORPHEME), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Institut de Biologie Valrose (IBV), Université Nice Sophia Antipolis (1965 - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (1965 - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Signal, Images et Systèmes (Laboratoire I3S - SIS), Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (1965 - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Centre National de la Recherche Scientifique (CNRS), and Calatroni, Luca
Subjects: [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], Computer Science::Computer Vision and Pattern Recognition, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Image denoising, Convolutional Neural Networks, [MATH.MATH-AP]Mathematics [math]/Analysis of PDEs [math.AP], [MATH.MATH-OC] Mathematics [math]/Optimization and Control [math.OC], [MATH.MATH-OC]Mathematics [math]/Optimization and Control [math.OC], [MATH.MATH-NA] Mathematics [math]/Numerical Analysis [math.NA], [MATH.MATH-AP] Mathematics [math]/Analysis of PDEs [math.AP], Local hyperparameter estimation, [MATH.MATH-NA]Mathematics [math]/Numerical Analysis [math.NA], Total Variation
Abstract: We consider the problem of image denoising with unknown noise distribution. We propose a hybrid approach where model-based space-variant total variation (TV) regularization is used for denoising with hyperparameters estimated locally using a Convolutional Neural Network (CNN) with a simple and light architecture. The special choice of the weighted TV prior allows for the use of a limited learning set, while the use of the proposed CNN approach allows for local parameter estimation independently of the type of noise in the data. The obtained results show that the proposed hybrid approach takes benefit from both the prior information encoded in the choice of the regularization model and the versatility of the CNN-based parameter estimation approach.
Published: 2022

9. Une forme de référence mutuelle pour la fusion et l'évaluation des méthodes de segmentation

Author: Jehan-Besson, S., Clouard, R., Tilmant, C., de Cesare, A., Lalande, A., Lebenberg, J., Clarysse, P., Sarry, L., Frouin, F., Garreau, M., Laboratoire d'Imagerie Translationnelle en Oncologie (LITO ), Institut Curie [Paris]-Institut National de la Santé et de la Recherche Médicale (INSERM), Institut Curie [Paris], Equipe Image - Laboratoire GREYC - UMR6072, Groupe de Recherche en Informatique, Image et Instrumentation de Caen (GREYC), Université de Caen Normandie (UNICAEN), Normandie Université (NU)-Normandie Université (NU)-École Nationale Supérieure d'Ingénieurs de Caen (ENSICAEN), Normandie Université (NU)-Centre National de la Recherche Scientifique (CNRS)-Université de Caen Normandie (UNICAEN), Normandie Université (NU)-Centre National de la Recherche Scientifique (CNRS), Institut Pascal (IP), Centre National de la Recherche Scientifique (CNRS)-Université Clermont Auvergne (UCA)-Institut national polytechnique Clermont Auvergne (INP Clermont Auvergne), Université Clermont Auvergne (UCA)-Université Clermont Auvergne (UCA), Laboratoire d'Imagerie Biomédicale [Paris] (LIB), Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Equipe IFTIM [ImViA - EA7535], Centre Hospitalier Universitaire de Dijon - Hôpital François Mitterrand (CHU Dijon)-Centre Régional de Lutte contre le cancer Georges-François Leclerc [Dijon] (UNICANCER/CRLCC-CGFL), UNICANCER-UNICANCER-Imagerie et Vision Artificielle [Dijon] (ImViA), Université de Bourgogne (UB)-Université de Bourgogne (UB), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Image Science for Interventional Techniques (ISIT), Université d'Auvergne - Clermont-Ferrand I (UdA)-Clermont Université-Centre National de la Recherche Scientifique (CNRS), Laboratoire Traitement du Signal et de l'Image (LTSI), Université de Rennes (UR)-Institut National de la Santé et de la Recherche Médicale (INSERM), Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Ingénieurs de Caen (ENSICAEN), Normandie Université (NU)-Normandie Université (NU)-Université de Caen Normandie (UNICAEN), Normandie Université (NU)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Ingénieurs de Caen (ENSICAEN), Normandie Université (NU), Université Blaise Pascal - Clermont-Ferrand 2 (UBP)-SIGMA Clermont (SIGMA Clermont)-Centre National de la Recherche Scientifique (CNRS), Laboratoire d'Imagerie Biomédicale (LIB), Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Pierre et Marie Curie - Paris 6 (UPMC), Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Imagerie et modélisation Vasculaires, Thoraciques et Cérébrales (MOTIVATE), Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM), Université d'Auvergne - Clermont-Ferrand I (UdA)-Centre National de la Recherche Scientifique (CNRS)-Clermont Université, Institut National de la Santé et de la Recherche Médicale (INSERM)-Université de Rennes 1 (UR1), and Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)
Subjects: active contours, variational approaches, segmentation evaluation, shape gradients, [INFO.INFO-IT]Computer Science [cs]/Information Theory [cs.IT], Computer Science::Computer Vision and Pattern Recognition, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Mutual shape, segmentation, shape optimization, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, segmentation fusion
Abstract: This paper proposes the estimation of a mutual shape from a set of different segmentation results using both active contours and information theory. The mutual shape is here defined as a consensus shape estimated from a set of different segmentations of the same object. In an original manner, such a shape is defined as the minimum of a criterion that benefits from both the mutual information and the joint entropy of the input segmentations. This energy criterion is justified using similarities between information theory quantities and area measures, and presented in a continuous variational framework. In order to solve this shape optimization problem, shape derivatives are computed for each term of the criterion and interpreted as an evolution equation of an active contour. A mutual shape is then estimated together with the sensitivity and specificity of each segmentation. Some synthetic examples allow us to cast the light on the difference between the mutual shape and an average shape. The applicability of our framework has also been tested for segmentation evaluation and fusion of different types of real images (natural color images, old manuscripts, medical images).
Published: 2022

10. A mutual reference shape for segmentation fusion and evaluation

Author: Jehan-Besson, S., Clouard, R., Tilmant, C., de Cesare, A., Lalande, A., Lebenberg, J., Clarysse, P., Sarry, L., Frouin, F., Garreau, M., Laboratoire d'Imagerie Translationnelle en Oncologie (LITO ), Institut Curie [Paris]-Institut National de la Santé et de la Recherche Médicale (INSERM), Institut Curie [Paris], Equipe Image - Laboratoire GREYC - UMR6072, Groupe de Recherche en Informatique, Image et Instrumentation de Caen (GREYC), Université de Caen Normandie (UNICAEN), Normandie Université (NU)-Normandie Université (NU)-École Nationale Supérieure d'Ingénieurs de Caen (ENSICAEN), Normandie Université (NU)-Centre National de la Recherche Scientifique (CNRS)-Université de Caen Normandie (UNICAEN), Normandie Université (NU)-Centre National de la Recherche Scientifique (CNRS), Institut Pascal (IP), Centre National de la Recherche Scientifique (CNRS)-Université Clermont Auvergne (UCA)-Institut national polytechnique Clermont Auvergne (INP Clermont Auvergne), Université Clermont Auvergne (UCA)-Université Clermont Auvergne (UCA), Laboratoire d'Imagerie Biomédicale (LIB), Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Equipe IFTIM [ImViA - EA7535], Centre Hospitalier Universitaire de Dijon - Hôpital François Mitterrand (CHU Dijon)-Centre Régional de Lutte contre le cancer Georges-François Leclerc [Dijon] (UNICANCER/CRLCC-CGFL), UNICANCER-UNICANCER-Imagerie et Vision Artificielle [Dijon] (ImViA), Université de Bourgogne (UB)-Université de Bourgogne (UB), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Image Science for Interventional Techniques (ISIT), Université d'Auvergne - Clermont-Ferrand I (UdA)-Clermont Université-Centre National de la Recherche Scientifique (CNRS), Laboratoire Traitement du Signal et de l'Image (LTSI), Université de Rennes (UR)-Institut National de la Santé et de la Recherche Médicale (INSERM), and Jehan-Besson, Stéphanie
Subjects: FOS: Computer and information sciences, segmentation evaluation, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [INFO.INFO-IM] Computer Science [cs]/Medical Imaging, 02 engineering and technology, Statistics - Applications, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, variational approaches, 0302 clinical medicine, shape gradients, Mutual shape, FOS: Electrical engineering, electronic engineering, information engineering, 0202 electrical engineering, electronic engineering, information engineering, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Applications (stat.AP), Image and Video Processing (eess.IV), segmentation, Electrical Engineering and Systems Science - Image and Video Processing, active contours, [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], [INFO.INFO-IT]Computer Science [cs]/Information Theory [cs.IT], Computer Science::Computer Vision and Pattern Recognition, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], shape optimization, 020201 artificial intelligence & image processing, [INFO.INFO-IT] Computer Science [cs]/Information Theory [cs.IT], segmentation fusion
Abstract: This paper proposes the estimation of a mutual shape from a set of different segmentation results using both active contours and information theory. The mutual shape is here defined as a consensus shape estimated from a set of different segmentations of the same object. In an original manner, such a shape is defined as the minimum of a criterion that benefits from both the mutual information and the joint entropy of the input segmentations. This energy criterion is justified using similarities between information theory quantities and area measures, and presented in a continuous variational framework. In order to solve this shape optimization problem, shape derivatives are computed for each term of the criterion and interpreted as an evolution equation of an active contour. A mutual shape is then estimated together with the sensitivity and specificity of each segmentation. Some synthetic examples allow us to cast the light on the difference between the mutual shape and an average shape. The applicability of our framework has also been tested for segmentation evaluation and fusion of different types of real images (natural color images, old manuscripts, medical images).
Published: 2022

11. Deep neural networks-based relevant latent representation learning for hyperspectral image classification

Author: Salvatore Tabbone, Akrem Sellami, Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), and Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)
Subjects: Computer science, hyperspectral image classification, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], representation learning, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Artificial Intelligence, Representation (mathematics), Spectral signature, Pixel, business.industry, feature extraction, Hyperspectral imaging, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, Deep learning, Spectral bands, Autoencoder, ComputingMethodologies_PATTERNRECOGNITION, Computer Science::Computer Vision and Pattern Recognition, Signal Processing, Graph (abstract data type), Computer Vision and Pattern Recognition, Artificial intelligence, business, Feature learning, Software
Abstract: International audience; The classification of hyperspectral image is a challenging task due to the high dimensional space, with large number of spectral bands, and low number of labeled training samples. To overcome these challenges, we propose a novel methodology for hyperspectral image classification based on multi-view deep neural networks which fuses both spectral and spatial features by using only a small number of labeled samples. Firstly, we process the initial hyperspectral image in order to extract a set of spectral and spatial features. Each spectral vector is the spectral signature of each pixel of the image. The spatial features are extracted using a simple deep autoencoder, which seeks to reduce the high dimensionality of data taking into account the neighborhood region for each pixel. Secondly, we propose a multi-view deep autoencoder model which allows fusing the spectral and spatial features extracted from the hyperspectral image into a joint latent representation space. Finally, a semi-supervised graph convolutional network is trained based on thee fused latent representation space to perform the hyperspectral image classification. The main advantage of the proposed approach is to allow the automatic extraction of relevant information while preserving the spatial and spectral features of data, and improve the classification of hyperspectral images even when the number of labeled samples is low. Experiments are conducted on three real hyperspectral images respectively Indian Pines, Salinas, and Pavia University datasets. Results show that the proposed approach is competitive in classification performances compared to state-of-the-art.
Published: 2022

12. Kalman Filtering and Expectation Maximization for Multitemporal Spectral Unmixing

Author: Jose C. M. Bermudez, Ricardo Augusto Borsoi, Tales Imbiriba, Cedric Richard, Pau Closas, Joseph Louis LAGRANGE (LAGRANGE), Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Observatoire de la Côte d'Azur, COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Université Côte d'Azur (UCA)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS), Universidade Federal de Santa Catarina = Federal University of Santa Catarina [Florianópolis] (UFSC), and Northeastern University [Boston]
Subjects: FOS: Computer and information sciences, Endmember, Bayesian filtering, Computer science, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, 0211 other engineering and technologies, Model parameters, 02 engineering and technology, Mixing (mathematics), Expectation–maximization algorithm, FOS: Electrical engineering, electronic engineering, information engineering, Electrical and Electronic Engineering, ComputingMilieux_MISCELLANEOUS, 021101 geological & geomatics engineering, Parametric statistics, business.industry, Image and Video Processing (eess.IV), Hyperspectral imaging, Pattern recognition, Kalman filter, Electrical Engineering and Systems Science - Image and Video Processing, Geotechnical Engineering and Engineering Geology, Computer Science::Computer Vision and Pattern Recognition, Artificial intelligence, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract: The recent evolution of hyperspectral imaging technology and the proliferation of new emerging applications presses for the processing of multiple temporal hyperspectral images. In this work, we propose a novel spectral unmixing (SU) strategy using physically motivated parametric endmember representations to account for temporal spectral variability. By representing the multitemporal mixing process using a state-space formulation, we are able to exploit the Bayesian filtering machinery to estimate the endmember variability coefficients. Moreover, by assuming that the temporal variability of the abundances is small over short intervals, an efficient implementation of the expectation maximization (EM) algorithm is employed to estimate the abundances and the other model parameters. Simulation results indicate that the proposed strategy outperforms state-of-the-art multitemporal SU algorithms.
Published: 2022

13. Binary Graph Descriptor for Robust Relocalization on Heterogeneous Data

Author: Xi Wang, Marc Christie, Eric Marchand, Analysis-Synthesis Approach for Virtual Human Simulation (MIMETIC), Université de Rennes 2 (UR2)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-RÉALITÉ VIRTUELLE, HUMAINS VIRTUELS, INTERACTIONS ET ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Sensor-based and interactive robotics (RAINBOW), Inria Rennes – Bretagne Atlantique, Université de Rennes 2 (UR2), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-MEDIA ET INTERACTIONS (IRISA-D6), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-MEDIA ET INTERACTIONS (IRISA-D6), and Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1)
Subjects: Human-Computer Interaction, Control and Optimization, Artificial Intelligence, Control and Systems Engineering, Mechanical Engineering, Computer Science::Computer Vision and Pattern Recognition, Biomedical Engineering, [INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO], Computer Vision and Pattern Recognition, Computer Science Applications
Abstract: International audience; In this paper, we propose a novel binary graph descriptor to improve loop detection for visual SLAM systems. Our contribution is twofold: i) a graph embedding technique for generating binary descriptors which conserve both spatial and histogram information extracted from images; ii) a generic mean of combining multiple layers of heterogeneous data into the proposed binary graph descriptor, coupled with a matching and geometric checking method. We also introduce an implementation of our descriptor into an incremental Bag-of-Words (iBoW) structure that improves efficiency and scalability, and propose a method to interpret Deep Neural Network (DNN) results. We evaluate our system on synthetic and real datasets across different lighting and seasonal conditions. The proposed method outperforms state-of-the-art loop detection frameworks in terms of relocalization precision and computational performance, as well as displays high robustness against cross-condition datasets.
Published: 2022

14. OSLO: On-the-Sphere Learning for Omnidirectional images and its application to 360-degree image compression

Author: Navid Mahmoudian Bidgoli, Roberto G. de A. Azevedo, Thomas Maugey, Aline Roumy, Pascal Frossard, Analysis representation, compression and communication of visual data (Sirocco), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAL, IMAGE ET LANGAGE (IRISA-D6), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Departement Erdwissenschaften [ETH Zürich] (D-ERDW), Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), Ecole Polytechnique Fédérale de Lausanne (EPFL), and This work was supported by the Cominlabs excellence laboratory with funding from the French National Research Agency (ANR-10-LABX-07-01), InterCom and MOVE projects.
Subjects: FOS: Computer and information sciences, 360-degree images, Computer Vision and Pattern Recognition (cs.CV), spherical convolution, Image and Video Processing (eess.IV), Computer Science::Neural and Evolutionary Computation, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Computer Science - Computer Vision and Pattern Recognition, [MATH.MATH-IT]Mathematics [math]/Information Theory [math.IT], complexity theory, Electrical Engineering and Systems Science - Image and Video Processing, Computer Graphics and Computer-Aided Design, kernel, Computer Science::Computer Vision and Pattern Recognition, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], convolutional neural networks, endto-end compression, FOS: Electrical engineering, electronic engineering, information engineering, task analysis, end-to-end compression, convolution, anisotropic filter, computer architecture, image coding, Software
Abstract: State-of-the-art 2D image compression schemes rely on the power of convolutional neural networks (CNNs). Although CNNs offer promising perspectives for 2D image compression, extending such models to omnidirectional images is not straightforward. First, omnidirectional images have specific spatial and statistical properties that can not be fully captured by current CNN models. Second, basic mathematical operations composing a CNN architecture, e.g., translation and sampling, are not well-defined on the sphere. In this paper, we study the learning of representation models for omnidirectional images and propose to use the properties of HEALPix uniform sampling of the sphere to redefine the mathematical tools used in deep learning models for omnidirectional images. In particular, we: i) propose the definition of a new convolution operation on the sphere that keeps the high expressiveness and the low complexity of a classical 2D convolution; ii) adapt standard CNN techniques such as stride, iterative aggregation, and pixel shuffling to the spherical domain; and then iii) apply our new framework to the task of omnidirectional image compression. Our experiments show that our proposed on-the-sphere solution leads to a better compression gain that can save 13.7% of the bit rate compared to similar learned models applied to equirectangular images. Also, compared to learning models based on graph convolutional networks, our solution supports more expressive filters that can preserve high frequencies and provide a better perceptual quality of the compressed images. Such results demonstrate the efficiency of the proposed framework, which opens new research venues for other omnidirectional vision tasks to be effectively implemented on the sphere manifold., Accepted for publication in IEEE Transactions on Image Processing
Published: 2022

15. Monocular Human Shape and Pose with Dense Mesh-borne Local Image Features

Author: Jena, Shubhendu, Multon, Franck, Boukhayma, Adnane, Analysis-Synthesis Approach for Virtual Human Simulation (MIMETIC), Université de Rennes 2 (UR2)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-MEDIA ET INTERACTIONS (IRISA-D6), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Laboratoire Mouvement Sport Santé (M2S), Université de Rennes (UR)-École normale supérieure - Rennes (ENS Rennes)-Université de Brest (UBO)-Université de Rennes 2 (UR2)-Structure Fédérative de Recherche en Biologie et Santé de Rennes ( Biosit : Biologie - Santé - Innovation Technologique ), Université de Rennes 2 (UR2), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Inria Rennes – Bretagne Atlantique, Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), École normale supérieure - Cachan (ENS Cachan)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Université de Brest (UBO)-Université de Rennes 2 (UR2), Université de Rennes (UNIV-RENNES)-Structure Fédérative de Recherche en Biologie et Santé de Rennes ( Biosit : Biologie - Santé - Innovation Technologique ), and Multon, Franck
Subjects: FOS: Computer and information sciences, [INFO.INFO-MM] Computer Science [cs]/Multimedia [cs.MM], Computer Vision and Pattern Recognition (cs.CV), Computer Science::Computer Vision and Pattern Recognition, Computer Science - Computer Vision and Pattern Recognition, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [INFO.INFO-MM]Computer Science [cs]/Multimedia [cs.MM]
Abstract: We propose to improve on graph convolution based approaches for human shape and pose estimation from monocular input, using pixel-aligned local image features. Given a single input color image, existing graph convolutional network (GCN) based techniques for human shape and pose estimation use a single convolutional neural network (CNN) generated global image feature appended to all mesh vertices equally to initialize the GCN stage, which transforms a template T-posed mesh into the target pose. In contrast, we propose for the first time the idea of using local image features per vertex. These features are sampled from the CNN image feature maps by utilizing pixel-to-mesh correspondences generated with DensePose. Our quantitative and qualitative results on standard benchmarks show that using local features improves on global ones and leads to competitive performances with respect to the state-of-the-art., Comment: FG 2021
Published: 2021

16. A spherical convolutional neural network for white matter structure imaging via dMRI

Author: Abib Alimi, Rachid Deriche, Théodore Papadopoulo, Samuel Deslauriers-Gauthier, Sara Sedlar, Computational Imaging of the Central Nervous System (ATHENA), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), This work was supported by the ERC under the European Union’s Horizon 2020 research and innovation program (ERC Advanced Grant agreement N°694665: CoBCoM : Computational Brain Connectivity Mapping).This work has been partly supported by the French government, through the3IA Côte d’Azur Investments in the Future project managed by the National Research Agency (ANR) with the reference number ANR-19-P3IA-0002.Data were provided [in part] by the Human Connectome Project, WU-Minn Consortium (Principal Investigators: David Van Essen and Kamil Ugurbil, 1U54MH091657) funded by the 16 NIH Institutes and Centers that support the NIH Blueprint for Neuroscience Research, and by the McDonnell Center for Systems Neuroscience at Washington University., Marleen de Bruijne, Philippe C. Cattin, Stéphane Cotin, Nicolas Padoy, Stefanie Speidel, Yefeng Zheng, Caroline Essert, ANR-19-P3IA-0002,3IA@cote d'azur,3IA Côte d'Azur(2019), and European Project: 694665,H2020 ERC,ERC-2015-AdG,CoBCoM(2016)
Subjects: Diffusion (acoustics), Human Connectome Project, Orientation (computer vision), business.industry, Computer science, [SCCO.NEUR]Cognitive science/Neuroscience, white matter micro-structures, Pattern recognition, Convolutional neural network, Spherical CNN, 030218 nuclear medicine & medical imaging, Regular grid, diffusion MRI, 03 medical and health sciences, 0302 clinical medicine, Sampling (signal processing), [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Computer Science::Computer Vision and Pattern Recognition, Rotational invariance, Artificial intelligence, business, 030217 neurology & neurosurgery, Diffusion MRI
Abstract: International audience; Diffusion Magnetic Resonance Imaging (dMRI) is a powerful non-invasive and in-vivo imaging modality for probing brain white matter structure. Convolutional neural networks (CNNs) have been shown to be a powerful tool for many computer vision problems where the signals are acquired on a regular grid and where translational invariance is important. However, as we are considering dMRI signals that are acquired on a sphere, rotational invariance, rather than translational, is desired. In this work, we propose a spherical CNN model with fully spectral domain convolutional and non-linear layers. It provides rotational invariance and is adapted to the real nature of dMRI signals and uniform random distribution of sampling points. The proposed model is positively evaluated on the problem of estimation of neurite orientation dispersion and density imaging (NODDI) parameters on the data from Human Connectome Project (HCP).
Published: 2021

17. Regularization via Deep Generative Models: an Analysis Point of View

Author: Thomas Oberlin, Mathieu Verm, Institut Supérieur de l'Aéronautique et de l'Espace (ISAE-SUPAERO), Signal et Communications (IRIT-SC), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, IEEE Signal Processing Society, ANR-19-P3IA-0004,ANITI,Artificial and Natural Intelligence Toulouse Institute(2019), Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Institut Supérieur de l'Aéronautique et de l'Espace - ISAE-SUPAERO (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), Université Toulouse - Jean Jaurès - UT2J (FRANCE), and Université Toulouse 1 Capitole - UT1 (FRANCE)
Subjects: FOS: Computer and information sciences, Inverse problems, Deblurring, Computer Science - Machine Learning, Computer science, Computer Vision and Pattern Recognition (cs.CV), [INFO.INFO-OH]Computer Science [cs]/Other [cs.OH], Inpainting, Computer Science - Computer Vision and Pattern Recognition, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Initialization, 02 engineering and technology, Data-driven priors, Regularization (mathematics), Image (mathematics), Machine Learning (cs.LG), Autre, Regularization, 0202 electrical engineering, electronic engineering, information engineering, FOS: Electrical engineering, electronic engineering, information engineering, Artificial neural network, Image and Video Processing (eess.IV), Generative models, 020207 software engineering, Inverse problem, Electrical Engineering and Systems Science - Image and Video Processing, Generative model, Deep regularization, Computer Science::Computer Vision and Pattern Recognition, 020201 artificial intelligence & image processing, Algorithm, Estimation
Abstract: International audience; This paper proposes a new way of regularizing an inverse problem in imaging (e.g., deblurring or inpainting) by means of a deep generative neural network. Compared to end-to-end models, such approaches seem particularly interesting since the same network can be used for many different problems and experimental conditions, as soon as the generative model is suited to the data. Previous works proposed to use a synthesis framework, where the estimation is performed on the latent vector, the solution being obtained afterwards via the decoder. Instead, we propose an analysis formulation where we directly optimize the image itself and penalize the latent vector. We illustrate the interest of such a formulation by running experiments of inpainting, deblurring and super-resolution. In many cases our technique achieves a clear improvement of the performance and seems to be more robust, in particular with respect to initialization.
Published: 2021

18. Image Denoising Inspired by Quantum Many-Body physics

Author: Adrian Basarab, Sayantan Dutta, Bertrand Georgeot, Denis Kouame, Laboratoire de Physique Théorique (LPT), Institut de Recherche sur les Systèmes Atomiques et Moléculaires Complexes (IRSAMC), Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées, CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, IEEE, Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Toulouse Mind & Brain Institut (TMBI), Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT), Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Fédération de recherche « Matière et interactions » (FeRMI), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), and Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)
Subjects: quantum denoising, Similarity (geometry), Computer science, Noise reduction, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Context (language use), Image processing, 02 engineering and technology, quantum image processing, symbols.namesake, [PHYS.QPHY]Physics [physics]/Quantum Physics [quant-ph], Digital image processing, 0202 electrical engineering, electronic engineering, information engineering, FOS: Electrical engineering, electronic engineering, information engineering, [INFO]Computer Science [cs], Noise (signal processing), Image and Video Processing (eess.IV), Wavelet transform, 020207 software engineering, Quantum many-body interaction, Electrical Engineering and Systems Science - Image and Video Processing, adaptive transform, Additive white Gaussian noise, Computer Science::Computer Vision and Pattern Recognition, symbols, 020201 artificial intelligence & image processing, Algorithm
Abstract: Decomposing an image through Fourier, DCT or wavelet transforms is still a common approach in digital image processing, in number of applications such as denoising. In this context, data-driven dictionaries and in particular exploiting the redundancy withing patches extracted from one or several images allowed important improvements. This paper proposes an original idea of constructing such an image-dependent basis inspired by the principles of quantum many-body physics. The similarity between two image patches is introduced in the formalism through a term akin to interaction terms in quantum mechanics. The main contribution of the paper is thus to introduce this original way of exploiting quantum many-body ideas in image processing, which opens interesting perspectives in image denoising. The potential of the proposed adaptive decomposition is illustrated through image denoising in presence of additive white Gaussian noise, but the method can be used for other types of noise such as image-dependent noise as well. Finally, the results show that our method achieves comparable or slightly better results than existing approaches., Comment: 5 pages, 4 figures
Published: 2021

19. A Registration Error Estimation Framework for Correlative Imaging

Author: Guillaume Potier, Frédéric Lavancier, Stephan Kunne, Perrine Paul-Gilloteaux, Unité de recherche de l'institut du thorax (ITX-lab), Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université de Nantes - UFR de Médecine et des Techniques Médicales (UFR MEDECINE), Université de Nantes (UN)-Université de Nantes (UN), Laboratoire de Mathématiques Jean Leray (LMJL), Université de Nantes - UFR des Sciences et des Techniques (UN UFR ST), Université de Nantes (UN)-Université de Nantes (UN)-Centre National de la Recherche Scientifique (CNRS), Structure fédérative de recherche François Bonamy (SFR François Bonamy), Université de Nantes (UN)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche en Santé de l'Université de Nantes (IRS-UN), ANR-18-CE45-0015,CROCOVAL,Recalage transmodal en microscopies corrélatives pour la caractérisation physiopathologique de la valvulopathie(2018), ANR-10-INBS-0004,France-BioImaging,Développment d'une infrastructure française distribuée coordonnée(2010), European Project: CA17121,COMULIS, Paul-Gilloteaux, Perrine, APPEL À PROJETS GÉNÉRIQUE 2018 - Recalage transmodal en microscopies corrélatives pour la caractérisation physiopathologique de la valvulopathie - - CROCOVAL2018 - ANR-18-CE45-0015 - AAPG2018 - VALID, Développment d'une infrastructure française distribuée coordonnée - - France-BioImaging2010 - ANR-10-INBS-0004 - INBS - VALID, COST COMULIS Correlated Multimodal Imaging in Life Science - COMULIS - CA17121 - INCOMING, unité de recherche de l'institut du thorax UMR1087 UMR6291 (ITX), Université de Nantes - UFR de Médecine et des Techniques Médicales (UFR MEDECINE), Université de Nantes (UN)-Université de Nantes (UN)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Centre National de la Recherche Scientifique (CNRS)-Université de Nantes - UFR des Sciences et des Techniques (UN UFR ST), and ANR-11-LABX-0020,LEBESGUE,Centre de Mathématiques Henri Lebesgue : fondements, interactions, applications et Formation(2011)
Subjects: Correlative, FOS: Computer and information sciences, Computer science, [SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging, Computer Vision and Pattern Recognition (cs.CV), [SDV]Life Sciences [q-bio], Computer Science - Computer Vision and Pattern Recognition, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Quantitative Biology - Quantitative Methods, Image (mathematics), [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [STAT.AP] Statistics [stat]/Applications [stat.AP], [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], 0202 electrical engineering, electronic engineering, information engineering, Computer vision, Point (geometry), [MATH.MATH-ST] Mathematics [math]/Statistics [math.ST], Quantitative Methods (q-bio.QM), [STAT.AP]Statistics [stat]/Applications [stat.AP], business.industry, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, Sample (graphics), [SDV] Life Sciences [q-bio], Transformation (function), Workflow, [SDV.IB.IMA] Life Sciences [q-bio]/Bioengineering/Imaging, [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], FOS: Biological sciences, Computer Science::Computer Vision and Pattern Recognition, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 020201 artificial intelligence & image processing, Artificial intelligence, Affine transformation, Noise (video), business
Abstract: Correlative imaging workflows are now widely used in bioimaging and aims to image the same sample using at least two different and complementary imaging modalities. Part of the workflow relies on finding the transformation linking a source image to a target image. We are specifically interested in the estimation of registration error in point-based registration. We propose an application of multivariate linear regression to solve the registration problem allowing us to propose a framework for the estimation of the associated error in the case of rigid and affine transformations and with anisotropic noise. These developments can be used as a decision-support tool for the biologist to analyze multimodal correlative images and are available under Ec-CLEM, an open-source plugin under ICY., Comment: 10 pages 2 figures (made of 10 panels in total)
Published: 2021

20. Comparison of photometric phase curves resulting from various observation scenes

Author: Potin, S, Douté, S, Kugler, Benoit, Forbes, Florence, University of Winnipeg, Institut de Planétologie et d'Astrophysique de Grenoble (IPAG), Centre National d'Études Spatiales [Toulouse] (CNES)-Observatoire des Sciences de l'Univers de Grenoble (OSUG ), Institut national des sciences de l'Univers (INSU - CNRS)-Université Savoie Mont Blanc (USMB [Université de Savoie] [Université de Chambéry])-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-Université Grenoble Alpes (UGA)-Institut national des sciences de l'Univers (INSU - CNRS)-Université Savoie Mont Blanc (USMB [Université de Savoie] [Université de Chambéry])-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-Université Grenoble Alpes (UGA), Laboratoire Jean Kuntzmann (LJK), Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP ), Université Grenoble Alpes (UGA), Modèles statistiques bayésiens et des valeurs extrêmes pour données structurées et de grande dimension (STATIFY), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK), Université Grenoble Alpes (UGA)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP ), and Institut national des sciences de l'Univers (INSU - CNRS)-Université Savoie Mont Blanc (USMB [Université de Savoie] [Université de Chambéry])-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-Université Grenoble Alpes (UGA)-Météo-France -Institut national des sciences de l'Univers (INSU - CNRS)-Université Savoie Mont Blanc (USMB [Université de Savoie] [Université de Chambéry])-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-Université Grenoble Alpes (UGA)-Météo-France
Subjects: [SDU]Sciences of the Universe [physics], [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], Computer Science::Computer Vision and Pattern Recognition, Physics::Space Physics, Astrophysics::Earth and Planetary Astrophysics, ComputingMilieux_MISCELLANEOUS
Abstract: International audience; The Solar System small bodies can be observed from ground-based or Earth orbiting telescopes but only span over a few pixels on the images due to their distance to the observer, their small size and atmospheric conditions blurring the images. The highest spatial resolution on the surface is achieved by in-situ observations by spacecrafts orbitting their target.
Published: 2021

21. A Tutorial on Applications of Power Watershed Optimization to Image Processing

Author: Aditya Challa, B. S. Daya Sagar, Sravan Danda, Laurent Najman, Birla Institute of Technology and Science (BITS Pilani), Indian Institute of Science [Bangalore] (IISc Bangalore), Indian Statistical Institute [Bangalore] (ISI), Laboratoire d'Informatique Gaspard-Monge (LIGM), and École des Ponts ParisTech (ENPC)-Centre National de la Recherche Scientifique (CNRS)-Université Gustave Eiffel
Subjects: Pixel, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, General Physics and Astronomy, 020207 software engineering, Image processing, 02 engineering and technology, Image segmentation, Random walker algorithm, Computer Science::Computer Vision and Pattern Recognition, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Shortest path problem, 0202 electrical engineering, electronic engineering, information engineering, Graph (abstract data type), 020201 artificial intelligence & image processing, General Materials Science, Segmentation, [MATH.MATH-OC]Mathematics [math]/Optimization and Control [math.OC], Physical and Theoretical Chemistry, Cluster analysis, Algorithm
Abstract: International audience; This tutorial review paper consolidates the existing applications of the power watershed (PW) optimization framework in the context of image processing. In literature, it is known that PW framework when applied to some well-known graph-based image segmentation and filtering algorithms such as random walker, isoperimetric partitioning, ratio-cut clustering, multi-cut and shortest path filters yield faster yet consistent solutions. In this paper, the intuition behind the working of PW framework i.e. exploitation of contrast invariance on image data is explained. The intuitions are illustrated with toy images and experiments on simulated astronomical images. This article is primarily aimed at researchers working on image segmentation and filtering problems in application areas such as astronomy where images typically havea huge number of pixels. Classic graph-based cost minimization methods provide good results on images with small number of pixels but do not scale well for images with large number of pixels. The ideas from the article can be adapted to a large class of graph-based cost minimization methods to obtain scalable segmentation and filtering algorithms.
Published: 2021

22. Hyperspectral Restoration and Fusion With Multispectral Imagery via Low-Rank Tensor-Approximation

Author: Wei Li, Ran Tao, Lu Li, Na Liu, James E. Fowler, Jocelyn Chanussot, Beijing University of Chemical Technology, Université Grenoble Alpes (UGA), Beijing Information Science and Technology University (BITSU), Beijing Institute of Technology (BIT), Mississippi State University [Mississippi], Laboratoire Jean Kuntzmann (LJK), Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP ), Chinese Academy of Sciences [Beijing] (CAS), GIPSA - Signal Images Physique (GIPSA-SIGMAPHY), GIPSA Pôle Sciences des Données (GIPSA-PSD), Grenoble Images Parole Signal Automatique (GIPSA-lab), Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP ), Université Grenoble Alpes (UGA)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP ), Université Grenoble Alpes (UGA)-Grenoble Images Parole Signal Automatique (GIPSA-lab), ANR-19-P3IA-0003,MIAI,MIAI @ Grenoble Alpes(2019), Apprentissage de modèles à partir de données massives (Thoth), Inria Grenoble - Rhône-Alpes, and Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK)
Subjects: Rank (linear algebra), business.industry, Computer science, Image quality, Multispectral image, 0211 other engineering and technologies, Hyperspectral imaging, Pattern recognition, 02 engineering and technology, Data fusion, low-rank tensor, Computer Science::Computer Vision and Pattern Recognition, Convex optimization, 0202 electrical engineering, electronic engineering, information engineering, General Earth and Planetary Sciences, hyperspectral imagery (HSI), 020201 artificial intelligence & image processing, Artificial intelligence, Tensor, Electrical and Electronic Engineering, business, Image resolution, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Image restoration, 021101 geological & geomatics engineering
Abstract: International audience; Tensor-based fusion that couples the high spatial resolution of a multispectral image (MSI) to the high spectral resolution of a hyperspectral image (HSI) is considered. The fusion problem is first formulated mathematically as a convex optimization of a tensor trace norm imposing low-rank spatially as well as spectrally, with an alternating-directions optimization featuring linearization providing the solution. Although prior tensor-based fusion approaches typically resort to tensor decomposition, the proposed algorithm exploits ideas from the field of tensor completion to directly impose a low-rank property spatially and spectrally while avoiding the computationally complex patch clustering and dictionary learning common to competing fusion techniques. Additionally, small modifications to the basic optimization permit a fusion process robust to missing hyperspectral values such as those that can result from dead stripes in real hyperspectral sensors. The experimental evaluations on both synthetic imagery as well as real imagery demonstrate that the resulting low-rank tensor-approximation (LRTA) fusion algorithm preserves both spatial details and texture, yielding significantly improved image quality when compared to other state-of-the-art fusion methods as well as effective restoration under conditions of missing stripes within the HSI.
Published: 2021

23. Stochastic permutation ordering watershed

Author: Lézoray, Olivier, Equipe Image - Laboratoire GREYC - UMR6072, Groupe de Recherche en Informatique, Image et Instrumentation de Caen (GREYC), Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Ingénieurs de Caen (ENSICAEN), Normandie Université (NU)-Normandie Université (NU)-Université de Caen Normandie (UNICAEN), Normandie Université (NU)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Ingénieurs de Caen (ENSICAEN), Normandie Université (NU), and Lezoray, Olivier
Subjects: Physics::Popular Physics, Segmentation, [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], Computer Science::Computer Vision and Pattern Recognition, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 0202 electrical engineering, electronic engineering, information engineering, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Hamiltonian path, 020206 networking & telecommunications, 020201 artificial intelligence & image processing, 02 engineering and technology, Computer Science::Computational Geometry, stochastic watershed
Abstract: International audience; The stochastic watershed is a morphological approach to segmentation that repeats the application of a seeded watershed from series of uniform random markers. The obtained watershed boundaries are combined to construct a probability density function. We propose an alternative approach called stochastic permutation ordering watershed. Our approach relies on the construction of several permutation orderings of the pixels of an image, starting from a random pixel and using a dedicated Hamiltonian path construction on a graph. From the permutation orderings, several seeded watersheds are applied and averaged. In contrast to the stochastic watershed, our approach enables to take into account any features associated to pixels, such as patches, of prime important to segment textured images. Experimental results show the benefit of the approach.
Published: 2021

24. The retina as a dynamical system

Author: Cessac, Bruno, Biologically plausible Integrative mOdels of the Visual system : towards synergIstic Solutions for visually-Impaired people and artificial visiON (BIOVISION), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), and Cessac, Bruno
Subjects: Quantitative Biology::Neurons and Cognition, [MATH.MATH-DS]Mathematics [math]/Dynamical Systems [math.DS], [PHYS.MPHY]Physics [physics]/Mathematical Physics [math-ph], [MATH.MATH-DS] Mathematics [math]/Dynamical Systems [math.DS], [PHYS.MPHY] Physics [physics]/Mathematical Physics [math-ph], [PHYS.COND.CM-DS-NN] Physics [physics]/Condensed Matter [cond-mat]/Disordered Systems and Neural Networks [cond-mat.dis-nn], FOS: Biological sciences, Computer Science::Computer Vision and Pattern Recognition, Quantitative Biology - Neurons and Cognition, Neurons and Cognition (q-bio.NC), [SDV.NEU]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC], [SDV.NEU] Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC], [PHYS.COND.CM-DS-NN]Physics [physics]/Condensed Matter [cond-mat]/Disordered Systems and Neural Networks [cond-mat.dis-nn], ComputingMilieux_MISCELLANEOUS
Abstract: Considering the retina as a high dimensional, non autonomous, dynamical system, layered and structured, with non stationary and spatially inhomogeneous entries (visual scenes), we present several examples where dynamical systems-, bifurcations-, and ergodic-theory provide useful insights on retinal behaviour and dynamics., Review paper, submitted as a chapter of the "Book in honour of Prof. Miguel A.F. Sanju\'an on his 60th Birthday"
Published: 2021

25. Biometric Masterkeys

Author: Tanguy Gernot, Patrick Lacharme, Equipe SAFE - Laboratoire GREYC - UMR6072, Groupe de Recherche en Informatique, Image et Instrumentation de Caen (GREYC), Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Ingénieurs de Caen (ENSICAEN), Normandie Université (NU)-Normandie Université (NU)-Université de Caen Normandie (UNICAEN), Normandie Université (NU)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Ingénieurs de Caen (ENSICAEN), and Normandie Université (NU)
Subjects: FOS: Computer and information sciences, [INFO.INFO-CR]Computer Science [cs]/Cryptography and Security [cs.CR], Computer Science - Cryptography and Security, General Computer Science, Computer Science::Computer Vision and Pattern Recognition, Data_MISCELLANEOUS, Masterkey, Law, Cryptography and Security (cs.CR), Biometric Authentication, Cancelable Biometric Transformation, Computer Science::Databases, Computer Science::Cryptography and Security
Abstract: Biometric authentication is used to secure digital or physical access. Such an authentication system uses a biometric database, where data are sometimes protected by cancelable transformations. This paper introduces the notion of biometric masterkeys. A masterkey is a feature vector such that the corresponding template matches with a significant number of templates stored in a cancelable biometric database. Such a masterkey is directly researched from a cancelable biometric database, but we also investigate another scenario in which the masterkey is fixed before the creation of the cancelable biometric database, providing additional access rights in the system for the masterkey's owner. Experimental results on the fingerprint database FVC and the face image database LFW show the effectiveness and the efficiency of such masterkeys in both scenarios. In particular, from any given feature vector, we are able to construct a cancelable database, for which the biometric template matches with all the templates of the database.
Published: 2021

26. Region-of-Interest CT Reconstruction using One-Endpoint Hilbert Inversion in Optimized Directions

Author: Coussat, Aurélien, Rit, Simon, Defrise, Michel, Létang, Jean Michel, Létang, Jean, Imagerie Tomographique et Radiothérapie, Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS), Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM), and Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Université Claude Bernard Lyon 1 (UCBL)
Subjects: Computer Science::Computer Vision and Pattern Recognition, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging
Abstract: International audience; In computed tomography, scanning the entire object is sometimes impossible, causing truncated projection data. Reconstruction is however still possible: using differentiated backprojection, the Hilbert transform of the object can be calculated and inverted along line segments in the field-of-view. When two endpoints of the line segment are outside the object extent, a stable analytic reconstruction formula exists. When only one endpoint is outside the object extent, every pixel can be reconstructed, but no inversion formula is known yet. Uniqueness of the inverse Hilbert transform is nevertheless guaranteed along such segments, and a numerical inverse can be used. Most pixels of the field-of-view accept more than one "one-endpoint line segment" and one can choose the direction; we propose here to select the optimal direction based on an empirical criterion. Image quality improvement is assessed against a reconstruction that uses a single direction for every pixel.
Published: 2021

27. Flat morphological operators from non-increasing set operators, I: general theory

Author: Christian Ronse, Laboratoire des sciences de l'ingénieur, de l'informatique et de l'imagerie (ICube), Institut National des Sciences Appliquées - Strasbourg (INSA Strasbourg), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Strasbourg (UNISTRA)-Centre National de la Recherche Scientifique (CNRS)-École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES)-Réseau nanophotonique et optique, Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Matériaux et nanosciences d'Alsace (FMNGE), Institut de Chimie du CNRS (INC)-Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Institut de Chimie du CNRS (INC)-Université de Strasbourg (UNISTRA)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), univOAK, Archive ouverte, École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES)-Université de Strasbourg (UNISTRA)-Institut National des Sciences Appliquées - Strasbourg (INSA Strasbourg), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Les Hôpitaux Universitaires de Strasbourg (HUS)-Centre National de la Recherche Scientifique (CNRS)-Matériaux et Nanosciences Grand-Est (MNGE), Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut de Chimie du CNRS (INC)-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut de Chimie du CNRS (INC)-Centre National de la Recherche Scientifique (CNRS)-Réseau nanophotonique et optique, and Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Centre National de la Recherche Scientifique (CNRS)
Subjects: Pure mathematics, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Set operators, poset, 0202 electrical engineering, electronic engineering, information engineering, bounded variation, QA1-939, 06b23, 06f20, Mathematics, summation, 020206 networking & telecommunications, operator on sets, 68u10, flat morphological operator, General theory, [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], Computer Science::Computer Vision and Pattern Recognition, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Bounded variation, 020201 artificial intelligence & image processing, Partially ordered set, Morphological operators, 26a45, 06e30
Abstract: Flat morphology is a general method for obtaining increasing operators on grey-level or multivalued images from increasing operators on binary images (or sets). It relies on threshold stacking and superposition; equivalently, Boolean max and min operations are replaced by lattice-theoretical sup and inf operations. In this paper we consider the construction a flat operator on grey-level or colour images from an operator on binary images that is not increasing. Here grey-level and colour images are functions from a space to an interval in ℝ m or ℤ m (m ≥ 1). Two approaches are proposed. First, we can replace threshold superposition by threshold summation. Next, we can decompose the non-increasing operator on binary images into a linear combination of increasing operators, then apply this linear combination to their flat extensions. Both methods require the operator to have bounded variation, and then both give the same result, which conforms to intuition. Our approach is very general, it can be applied to linear combinations of flat operators, or to linear convolution filters. Our work is based on a mathematical theory of summation of real-valued functions of one variable ranging in a poset. In a second paper, we will study some particular properties of non-increasing flat operators.
Published: 2021

28. Data Uncertainty Guided Noise-aware Preprocessing Of Fingerprints

Author: Ayush Utkarsh, Prem Kalra, Riya Kothari, Vinod K Kurmi, Antitza Dantcheva, Indu Joshi, Sumantra Dutta Roy, Spatio-Temporal Activity Recognition Systems (STARS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Indian Institute of Technology Delhi (IIT Delhi), Chercheur indépendant, University of Southern California (USC), Indian Institute of Technology Kanpur (IIT Kanpur), and ANR-18-CE92-0024,RESPECT,Authentification multi-biométrique des personnes, fiable, sécurisée et préservant la vie privée(2018)
Subjects: FOS: Computer and information sciences, Matching (statistics), Computer Science - Artificial Intelligence, Computer science, Computer Vision and Pattern Recognition (cs.CV), Data_MISCELLANEOUS, Computer Science - Computer Vision and Pattern Recognition, 02 engineering and technology, Fingerprint Enhancement, Background noise, Computer Science::Multimedia, 0202 electrical engineering, electronic engineering, information engineering, Preprocessor, [INFO]Computer Science [cs], Fingerprint Segmentation, Computer Science::Cryptography and Security, Pixel, business.industry, Fingerprint (computing), Pattern recognition, Image segmentation, Fingerprint recognition, Noise, Artificial Intelligence (cs.AI), Biometrics, Computer Science::Computer Vision and Pattern Recognition, Uncertainty Estimation, 020201 artificial intelligence & image processing, Artificial intelligence, business
Abstract: The effectiveness of fingerprint-based authentication systems on good quality fingerprints is established long back. However, the performance of standard fingerprint matching systems on noisy and poor quality fingerprints is far from satisfactory. Towards this, we propose a data uncertainty-based framework which enables the state-of-the-art fingerprint preprocessing models to quantify noise present in the input image and identify fingerprint regions with background noise and poor ridge clarity. Quantification of noise helps the model two folds: firstly, it makes the objective function adaptive to the noise in a particular input fingerprint and consequently, helps to achieve robust performance on noisy and distorted fingerprint regions. Secondly, it provides a noise variance map which indicates noisy pixels in the input fingerprint image. The predicted noise variance map enables the end-users to understand erroneous predictions due to noise present in the input image. Extensive experimental evaluation on 13 publicly available fingerprint databases, across different architectural choices and two fingerprint processing tasks demonstrate effectiveness of the proposed framework., IJCNN 2021 (Accepted)
Published: 2021

29. Classification and Generation of Earth Observation Images using a Joint Energy-Based Model

Author: Javiera Castillo-Navarro, Bertrand Le Saux, Sébastien Lefèvre, Alexandre Boulch, Observation de l’environnement par imagerie complexe (OBELIX), SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), DTIS, ONERA, Université Paris Saclay [Palaiseau], ONERA-Université Paris-Saclay, European Space Research Institute (ESRIN), European Space Agency (ESA), Valeo.ai, VALEO, Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), and Agence Spatiale Européenne = European Space Agency (ESA)
Subjects: Earth observation, 010504 meteorology & atmospheric sciences, Computer science, 0211 other engineering and technologies, Image registration, 02 engineering and technology, computer.software_genre, 01 natural sciences, Image (mathematics), Deep Learning, Generative Models, 021101 geological & geomatics engineering, 0105 earth and related environmental sciences, Energy-based Models, Artificial neural network, business.industry, Deep learning, 15. Life on land, Range (mathematics), Computer Science::Computer Vision and Pattern Recognition, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Benchmark (computing), Earth Observation, Artificial intelligence, Data mining, business, computer, Energy (signal processing)
Abstract: International audience; Deep learning has changed unbelievably the processing of Earth Observation tasks such as land cover mapping or image registration. Yet, today new models are needed to push further the revolution and enable new possibilities. We propose a new framework for generative modelling of Earth Observation images. It learns an energy-based model to estimate the underlying distribution of the data while jointly training a deep neural network for classification. On the varied image types of the EuroSAT benchmark, we show this model obtains classification results on par with state-of-the-art and moreover allows us to tackle a wide range of high-potential applications: image synthesis, out-of-distribution testing for domain adaptation, and image completion or denoising.
Published: 2021

30. Fast, Frugal Image Reconstruction with a Dual Disperser Hyperspectral Imager

Author: Antoine Monmayrant, Hervé Carfantan, Ibrahim Ardi, Elizabeth Hemsley, Simon Lacroix, Équipe Photonique (LAAS-PHOTO), Laboratoire d'analyse et d'architecture des systèmes (LAAS), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT), Institut de recherche en astrophysique et planétologie (IRAP), Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire Midi-Pyrénées (OMP), Institut de Recherche pour le Développement (IRD)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Institut de Recherche pour le Développement (IRD)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Centre National de la Recherche Scientifique (CNRS), Équipe Robotique et InteractionS (LAAS-RIS), Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Institut national des sciences de l'Univers (INSU - CNRS)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Observatoire Midi-Pyrénées (OMP), and Météo France-Centre National d'Études Spatiales [Toulouse] (CNES)-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche pour le Développement (IRD)-Météo France-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche pour le Développement (IRD)-Centre National de la Recherche Scientifique (CNRS)
Subjects: [PHYS.PHYS.PHYS-OPTICS]Physics [physics]/Physics [physics]/Optics [physics.optics], Computer science, business.industry, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Hyperspectral imaging, Disperser, Iterative reconstruction, Regularization (mathematics), Panchromatic film, Data cube, Compressed sensing, Computer Science::Computer Vision and Pattern Recognition, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Computer vision, Segmentation, Artificial intelligence, business
Abstract: International audience; Recently we demonstrated the reconstruction of a hyperspectral datacube with 110 wavelength bands from 10 camera acquisitions [1] . The implementation of this scheme, similarly to compressed sensing, relies on spatial- spectral correlations within the scene. A digital micro-mirror device (DMD) provides programmable spatial- spectral filtering, and is optimized to improve both the speed and accuracy of the reconstruction. Contrary to widespread approaches based on compressed sensing with a single disperser, our dual disperser architecture, illus- trated in Figure 1a , allows straightforward access the panchromatic image and simpler reconstruction algorithms. In particular, we harnessed the panchromatic image to develop a simple edge-preserving quadratic regularization, which is faster than ℓ 1 regularization and does not assume any sparse basis.
Published: 2021

31. Polygonal Building Segmentation by Frame Field Learning

Author: Girard, Nicolas, Smirnov, Dmitriy, Solomon, Justin, Tarabalka, Yuliya, COMUE Université Côte d'Azur (2015-2019) (COMUE UCA), Geometric Modeling of 3D Environments (TITANE), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Computer Science and Artificial Intelligence Laboratory [Cambridge] (CSAIL), Massachusetts Institute of Technology (MIT), Luxcarta technology [Mouans-Sartoux] (LCT), Thanks to ANR for funding the project EPITOME ANR-17-CE23-0009 and to Inria Sophia Antipolis - Méditerranée 'Nef' computation cluster for providing resources and support. The MIT Geometric Data Processing group acknowledges the generous support of Army Research Office grantW911NF2010168, of Air Force Office of Scientific Research award FA9550-19-1-031, of National Science Foundation grant IIS-1838071, from the CSAIL Systems that Learn program, from the MIT–IBM Watson AI Laboratory, from the Toyota–CSAIL Joint Research Center, from a gift from Adobe Systems, from an MIT.nano Immersion Lab/NCSOFT Gaming Program seed grant, and from the Skoltech–MIT Next Generation Program. This work was also supported by the National Science Foundation Graduate Research Fellowship under Grant No. 1122374., ANR-19-P3IA-0002 - 3IA Côte d'Azur - Nice - Interdisciplinary Institute for Artificial Intelligence, ANR-17-CE23-0009,EPITOME,Représentation efficace pour des images satellites à grande échelle(2017), ANR-19-P3IA-0002,3IA@cote d'azur,3IA Côte d'Azur(2019), and COMUE Université Côte d'Azur (2015 - 2019) (COMUE UCA)
Subjects: FOS: Computer and information sciences, Computer Science - Machine Learning, PolyVector field, Computer Vision and Pattern Recognition (cs.CV), Image and Video Processing (eess.IV), segmentation, Computer Science - Computer Vision and Pattern Recognition, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], frame field, polygonization, Electrical Engineering and Systems Science - Image and Video Processing, Machine Learning (cs.LG), regularization, remote sensing, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Computer Science::Computer Vision and Pattern Recognition, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], FOS: Electrical engineering, electronic engineering, information engineering
Abstract: While state of the art image segmentation models typically output segmentations in raster format, applications in geographic information systems often require vector polygons. To help bridge the gap between deep network output and the format used in downstream tasks, we add a frame field output to a deep segmentation model for extracting buildings from remote sensing images. We train a deep neural network that aligns a predicted frame field to ground truth contours. This additional objective improves segmentation quality by leveraging multi-task learning and provides structural information that later facilitates polygonization; we also introduce a polygonization algorithm that utilizes the frame field along with the raster segmentation. Our code is available at https://github.com/Lydorn/Polygonization-by-Frame-Field-Learning., Comment: CVPR 2021 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2021, Pittsburg / Virtual, United States
Published: 2021

32. Fast Pattern Spectra using Tree Representation of the Image for Patch Retrieval

Author: Jérôme Moré, Behzad Mirmahboub, David Youssefi, François Merciol, Sébastien Lefèvre, Alain Giros, Observation de l’environnement par imagerie complexe (OBELIX), SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Centre National d'Études Spatiales [Toulouse] (CNES), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), and Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes)
Subjects: Selection (relational algebra), Computer science, Computation, 0211 other engineering and technologies, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, large satellite images, Content-based image retrieval, Image (mathematics), Tree representation, pattern spectra, Histogram, 0202 electrical engineering, electronic engineering, information engineering, 021101 geological & geomatics engineering, business.industry, Pattern recognition, Object detection, tree representation, patch retrieval, Tree (data structure), Computer Science::Computer Vision and Pattern Recognition, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 020201 artificial intelligence & image processing, content based image retrieval, Artificial intelligence, business
Abstract: International audience; We extend the notion of content based image retrieval to patch retrieval where the goal is to find the similar patches to a query patch in a large image. Naive searching for similar patches by sequentially computing and comparing descriptors of sliding windows takes a lot of time in a large image. We propose a novel method to compute descriptors for all sliding windows independent from number of patches. We rely on tree representation of the image and exploit the histogram nature of pattern spectra to compute all the required descriptors in parallel. Computation time of the proposed method depends only on the number of tree nodes and is free from query selection. Experimental results show the effectiveness of the proposed method to reduce the computation time and its potential for object detection in large images.
Published: 2021

33. Learning local regularization for variational image restoration

Author: Prost, Jean, Houdard, Antoine, Almansa, Andrés, Papadakis, Nicolas, Institut de Mathématiques de Bordeaux (IMB), Université Bordeaux Segalen - Bordeaux 2-Université Sciences et Technologies - Bordeaux 1-Université de Bordeaux (UB)-Institut Polytechnique de Bordeaux (Bordeaux INP)-Centre National de la Recherche Scientifique (CNRS), Springer, and ANR-19-CE23-0027,PostProdLEAP,Repenser la post-production d'archives avec des méthodes à patch, variationnelles et par apprentissage(2019)
Subjects: FOS: Computer and information sciences, Computer Science - Machine Learning, deblurring, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Computer Science::Computer Vision and Pattern Recognition, Image and Video Processing (eess.IV), FOS: Electrical engineering, electronic engineering, information engineering, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, denoising, Electrical Engineering and Systems Science - Image and Video Processing, image inverse problem, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Machine Learning (cs.LG)
Abstract: In this work, we propose a framework to learn a local regularization model for solving general image restoration problems. This regularizer is defined with a fully convolutional neural network that sees the image through a receptive field corresponding to small image patches. The regularizer is then learned as a critic between unpaired distributions of clean and degraded patches using a Wasserstein generative adversarial networks based energy. This yields a regularization function that can be incorporated in any image restoration problem. The efficiency of the framework is finally shown on denoising and deblurring applications., 12 pages, 5 figures
Published: 2021

34. Geometric Deformation on Objects: Unsupervised Image Manipulation via Conjugation

Author: Laurent D. Cohen, Changqing Fu, CEntre de REcherches en MAthématiques de la DEcision (CEREMADE), Centre National de la Recherche Scientifique (CNRS)-Université Paris Dauphine-PSL, Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL), Université Paris Dauphine-PSL, and Université Paris sciences et lettres (PSL)
Subjects: Computer science, Transferability, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Image deformation, 02 engineering and technology, 010501 environmental sciences, Deformation (meteorology), 01 natural sciences, Image (mathematics), Machine Learning, Image Generation, 0202 electrical engineering, electronic engineering, information engineering, [MATH.MATH-AP]Mathematics [math]/Analysis of PDEs [math.AP], Computer vision, Representation (mathematics), 0105 earth and related environmental sciences, Image manipulation, business.industry, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Generative Adversarial Network, Computer Science::Computer Vision and Pattern Recognition, Contour Editing, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 020201 artificial intelligence & image processing, Artificial intelligence, Edge space, business, Generative adversarial network
Abstract: International audience; A novel two-stage approach is proposed for image manipulation and generation. User-interactive image deformation is performed through editing of contours. This is performed in the latent edge space with both color and gradient information. The output of editing is then fed into a multi-scale representation of the image to recover quality output. The model is flexible in terms of transferability and training efficiency.
Published: 2021

35. Model-image registration of a building’s facade based on dense semantic segmentation

Author: Gilles Simon, Marie-Odile Berger, Antoine Fond, Recalage visuel avec des modèles physiquement réalistes (TANGRAM), Inria Nancy - Grand Est, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Department of Algorithms, Computation, Image and Geometry (LORIA - ALGO), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS), Synthesia, The work of Antoine Fond was funded by the French Ministère de l'Enseignement supérieur, de la Recherche et de l'Innovation and by Inria., Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), and Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS)
Subjects: Image Registration, Computer science, Gaussian, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Image registration, 02 engineering and technology, Bayesian inference, symbols.namesake, Robustness (computer science), 0202 electrical engineering, electronic engineering, information engineering, Segmentation, Computer vision, business.industry, Camera Pose Estimation, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, Computer Science::Computer Vision and Pattern Recognition, Signal Processing, symbols, Global Positioning System, Clutter, 020201 artificial intelligence & image processing, Facade, Semantic Segmentation, Computer Vision and Pattern Recognition, Artificial intelligence, business, Software
Abstract: International audience; This article presents an efficient approach for accurate registration of a building facade model "dressed" with dense semantic information. Localization sensors such as the GPS as well as vision-based methods are able to provide a camera pose in an efficient and stable way, but at the expense of low accuracy. We propose here to rely on semantic maps to improve the accuracy of a rough camera pose. Simultaneously we aim to iteratively improve the quality of the semantic map through the registration. Registration and semantic segmentation are jointly refined in an Expectation-Maximization framework. We especially introduce a Bayesian model that uses prior semantic segmentation as well as geometric structure of the facade reference modeled by Generalized Gaussian Mixtures. We show the advantages of our method in terms of robustness to clutter and change of illumination on urban images from various databases.
Published: 2021

36. Adaptive target detection in hyperspectral imaging from two sets of training samples with different means

Author: François Vincent, Olivier Besson, Stefania Matteoli, Institut Supérieur de l'Aéronautique et de l'Espace (ISAE-SUPAERO), Institute of Electronics, Computer and Telecommunication Engineering [Milano] (IEIIT-CNR ), Consiglio Nazionale delle Ricerche [Torino] (CNR), Consiglio Nazionale delle Ricerche - CNR (ITALY), Institut Supérieur de l'Aéronautique et de l'Espace - ISAE-SUPAERO (FRANCE), and Département d'Electronique, Optronique et Signal - DEOS (Toulouse, France)
Subjects: Generalized likelihood ratio test, Hyperspectral imaging, Gaussian, 02 engineering and technology, Constant false alarm rate, Set (abstract data type), symbols.namesake, adaptive algortihms, remote sensing, [SPI]Engineering Sciences [physics], 0202 electrical engineering, electronic engineering, information engineering, Traitement du signal et de l'image, Electrical and Electronic Engineering, Mathematics, Spectral signature, Pixel, business.industry, target detection, 020206 networking & telecommunications, Pattern recognition, Covariance, Detection, hyperspectral, Control and Systems Engineering, Likelihood-ratio test, Computer Science::Computer Vision and Pattern Recognition, Signal Processing, symbols, 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Artificial intelligence, business, Software, Student distribution
Abstract: In this paper, we consider local detection of a target in hyperspectral imaging and we assume that the spectral signature of interest is buried in a background which follows an elliptically contoured distribution with unknown parameters. In order to infer the background parameters, two sets of training samples are available: one set, taken from pixels close to the pixel under test, shares the same mean and covariance while a second set of farther pixels shares the same covariance but has a different mean. When the whole data samples (pixel under test and training samples) follow a matrix-variate t distribution, the one-step generalized likelihood ratio test (GLRT) is derived in closed-form. It is shown that this GLRT coincides with that obtained under a Gaussian assumption and that it guarantees a constant false alarm rate. We also present a two-step GLRT where the mean and covariance of the background are estimated from the training samples only and then plugged in the GLRT based on the pixel under test only.
Published: 2021

37. Attention for Image Registration (AiR): A Transformer Approach

Author: Wang, Zihao, Delingette, Hervé, E-Patient : Images, données & mOdèles pour la médeciNe numériquE (EPIONE), Inria Sophia Antipolis - Méditerranée (CRISAM), and Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)
Subjects: Transformer, Deep Learning, Computer Science::Computer Vision and Pattern Recognition, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [INFO]Computer Science [cs], Images Registration
Abstract: Image registration as an important basis in signal processing task often encounter the problem of stability and efficiency. Non-learning registration approaches rely on the optimization of the similarity metrics between the fix-and moving images. Yet, those approaches are usually costly in both time and space complexity. The problem can be worse when the size of the image is large or the deformations between the images are severe. Recently, deep learning, or precisely saying, the convolutional neural network (CNN) based image registration methods have been widely investigated in the research community and show promising effectiveness to overcome the weakness of non-learning based methods. To explore the advanced learning approaches in image registration problem for solving practical issues, we present in this paper a method of introducing attention mechanism in deformable image registration problem. The proposed approach is based on learning the deformation field with a Transformer framework that does not rely on the CNN but can be efficiently trained on GPGPU devices also. Our method learns an artificially generated deformation map and tested it on a real-world dataset.
Published: 2021

38. Single-Pixel Image Reconstruction from Experimental Data Using Neural Networks

Author: Lorente Mur, Antonio, Leclerc, Pierre, PEYRIN, Françoise, Ducros, Nicolas, Imagerie Tomographique et Radiothérapie, Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), ANR-17-CE19-0003,Armoni,Acquisition Rapide d'images biomédicales par caméra MONo-pIxel(2017), ANR-11-LABX-0063,PRIMES,Physique, Radiobiologie, Imagerie Médicale et Simulation(2011), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Lorente Mur, Antonio, Acquisition Rapide d'images biomédicales par caméra MONo-pIxel - - Armoni2017 - ANR-17-CE19-0003 - AAPG2017 - VALID, Physique, Radiobiologie, Imagerie Médicale et Simulation - - PRIMES2011 - ANR-11-LABX-0063 - LABX - VALID, Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), and Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)
Subjects: [PHYS.PHYS.PHYS-OPTICS] Physics [physics]/Physics [physics]/Optics [physics.optics], [PHYS.PHYS.PHYS-OPTICS]Physics [physics]/Physics [physics]/Optics [physics.optics], [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Computer Science::Computer Vision and Pattern Recognition, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, [STAT.ML] Statistics [stat]/Machine Learning [stat.ML], [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing
Abstract: International audience; Single-pixel cameras that measure image coefficients have various promising applications, in particular for hyper-spectral imaging. Here, we investigate deep neural networks that when fed with experimental data, can output high-quality images in real time. Assuming that the measurements are corrupted by mixed Poisson-Gaussian noise, we propose to map the raw data from the measurement domain to the image domain based on a Tikhonov regularization. This step can be implemented as the first layer of a deep neural network, followed by any architecture of layers that acts in the image domain. We also describe a framework for training the network in the presence of noise. In particular, our approach includes an estimation of the image intensity and experimental parameters, together with a normalization scheme that allows varying noise levels to be handled during training and testing. Finally, we present results from simulations and experimental acquisitions with varying noise levels. Our approach yields images with improved peak signal-to-noise ratios, even for noise levels that were foreseen during the training of the networks, which makes the approach particularly suitable to deal with experimental data. Furthermore, while this approach focuses on single-pixel imaging, it can be adapted for other computational optics problems.
Published: 2021

39. DEEP EXPECTATION-MAXIMIZATION FOR IMAGE RECONSTRUCTION FROMUNDER-SAMPLED POISSON DATA

Author: Nicolas Ducros, Françoise Peyrin, Paul Bataille, Antonio Lorente Mur, Imagerie Tomographique et Radiothérapie, Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Lorente Mur, Antonio, Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), and Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)
Subjects: [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], model-based optimization meth- ods, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, convolutional neural network, Iterative reconstruction, Poisson distribution, 01 natural sciences, 030218 nuclear medicine & medical imaging, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], 010309 optics, 03 medical and health sciences, symbols.namesake, 0302 clinical medicine, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Hadamard transform, 0103 physical sciences, Expectation–maximization algorithm, Maximum a posteriori estimation, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Poisson noise, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing, Index Terms-Image reconstruction, Noise measurement, single-pixel imaging, Shot noise, deep learning, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], computational optics, expectation-maximization, Computer Science::Computer Vision and Pattern Recognition, Image reconstruction, symbols, Focus (optics), Algorithm, undersam- pled data, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract: International audience; We consider the reconstruction of an image from a sequence of a few linear measurements corrupted by Poisson noise. This generic problem has many biomedical applications, such as computerized tomography, positron emission tomogra-phy, and optical microscopy. Here, we focus on a computational optics problem where the setup acquires some coefficients of the Hadamard transform of the image of the scene. We formalize this problem in a Bayesian setting where we estimate the missing Hadamard coefficients from those acquired. Then, we propose a deep-learning network that consists of two fully connected layers (FCLs) that map data from the measurement domain to the image domain, followed by convolutional layers that act in the image domain. On the one hand, we set the FCLs so that they compute the best linear solution of the problem. While the first FCL denoises the raw measurements, the second FCL completes the missing measurements from the denoised measurements. The convolutional layers undergo learning through a training phase. We also describe a framework for training the network in the presence of Poisson noise. In particular, our approach includes an estimation of the image intensity, together with a normalization scheme that allows varying noise levels to be handled during training. We compare our network to linear reconstructors and to network variants that do not address the noise issue at all, or that address it implicitly. Finally, we present results from simulated and experimental acquisitions, considering varying noise levels. Our network yields higher reconstruction peak signal-to-noise ratios in scenarios where the actual noise level is higher than that expected and used during the training phase.
Published: 2021

40. Blind deconvolution using bilateral total variation regularization: a theoretical study and application

Author: Mohammed El Rhabi, Idriss El Mourabit, Abdelilah Hakim, Ecole Supérieure de Technologie d'Essaouira, Université Cadi Ayyad [Marrakech] (UCA), Innovation, Territoire, Agriculture et Agro-industrie, Connaissance et Technologie (INTERACT), UniLaSalle, and Laboratoire de Mathématiques Appliquées, Faculté des Sciences et Techniques, Université Cadi Ayyad (LAMAI)
Subjects: Blind deconvolution, Deblurring, Relaxation, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [MATH.MATH-FA]Mathematics [math]/Functional Analysis [math.FA], 01 natural sciences, Regularization (mathematics), Image (mathematics), Total Variation, Regularization, [MATH.MATH-AP]Mathematics [math]/Analysis of PDEs [math.AP], Computer vision, 0101 mathematics, [MATH]Mathematics [math], Mathematics, business.industry, Applied Mathematics, 010102 general mathematics, Relaxation (iterative method), Bilateral Total Variation, Total variation denoising, [INFO.INFO-NA]Computer Science [cs]/Numerical Analysis [cs.NA], Alternating Minimization, [INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation, 010101 applied mathematics, Kernel (image processing), Computer Science::Computer Vision and Pattern Recognition, Artificial intelligence, Deconvolution, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Analysis, [MATH.MATH-NA]Mathematics [math]/Numerical Analysis [math.NA]
Abstract: International audience; Blind image deconvolution recovers a deblurred image and the blur kernel from a blurred image. From a mathematical point of view, this is a strongly ill-posed problem and several works have been proposed to address it. One successful approach proposed by Chan and Wong, consists in using the total variation (TV) as a regularization for both the image and the kernel. These authors also introduced an Alternating Minimization (AM) algorithm in order to compute a physical solution. Unfortunately, Chanâs approach suffers in particular from the ringing and staircasing effects produced by the TV regularization. To address these problems, we propose a new model based on Bilateral Total Variation (BTV) regularization of the sharp image keeping the same regularization for the kernel. We prove the existence of a minimizer of a proposed variational problem in a suitable space using a relaxation process. We also propose an AM algorithm based on our model. The efficiency and robustness of our model are illustrated and compared with the TV method through numerical simulations.
Published: 2021

41. Quantum mechanics-based signal and image representation: application to denoising

Author: Adrian Basarab, Bertrand Georgeot, Sayantan Dutta, Denis Kouame, CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Toulouse Mind & Brain Institut (TMBI), Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT), Information et Chaos Quantiques (LPT), Laboratoire de Physique Théorique (LPT), Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Fédération de recherche « Matière et interactions » (FeRMI), Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université Toulouse III - Paul Sabatier (UT3), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées, Institut de Recherche sur les Systèmes Atomiques et Moléculaires Complexes (IRSAMC), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche sur les Systèmes Atomiques et Moléculaires Complexes (IRSAMC), and Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)
Subjects: Signal Processing (eess.SP), Computer science, Noise reduction, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Image processing, 02 engineering and technology, Signal, [SPI]Engineering Sciences [physics], Wavelet, [PHYS.QPHY]Physics [physics]/Quantum Physics [quant-ph], Quantum mechanics, FOS: Electrical engineering, electronic engineering, information engineering, 0202 electrical engineering, electronic engineering, information engineering, denoising, [INFO]Computer Science [cs], Electrical Engineering and Systems Science - Signal Processing, Signal processing, Basis (linear algebra), adaptive signal and image representation, Image and Video Processing (eess.IV), quantum mechanics, 020206 networking & telecommunications, Speckle noise, Total variation denoising, Electrical Engineering and Systems Science - Image and Video Processing, TK1-9971, adaptive transformation, Computer Science::Computer Vision and Pattern Recognition, 020201 artificial intelligence & image processing, Electrical engineering. Electronics. Nuclear engineering
Abstract: Decomposition of digital signals and images into other basis or dictionaries than time or space domains is a very common approach in signal and image processing and analysis. Such a decomposition is commonly obtained using fixed transforms (e.g., Fourier or wavelet) or dictionaries learned from example databases or from the signal or image itself. In this work, we investigate in detail a new approach of constructing such a signal or image-dependent bases inspired by quantum mechanics tools, i.e., by considering the signal or image as a potential in the discretized Schroedinger equation. To illustrate the potential of the proposed decomposition, denoising results are reported in the case of Gaussian, Poisson, and speckle noise and compared to the state of the art algorithms based on wavelet shrinkage, total variation regularization or patch-wise sparse coding in learned dictionaries, non-local means image denoising, and graph signal processing., 17 pages, 18 figures; complements and expands arXiv:1802.02358
Published: 2021

42. Mueller micropolarimeter for color imaging of aluminium metasurfaces

Author: W. Daney de Marcillac, M. Nicolas, G. Guida, Dominique Demaille, I. Soumahoro, L. Zhang, S. Boujday, Bruno Gallas, Catherine Schwob, Nanostructures et optique (INSP-E4), Institut des Nanosciences de Paris (INSP), Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Université Nangui Abrogoua, Laboratoire Energétique Mécanique Electromagnétisme (LEME), Université Paris Nanterre (UPN), Croissance et propriétés de systèmes hybrides en couches minces (INSP-E8), Laboratoire de Réactivité de Surface (LRS), Institut de Chimie du CNRS (INC)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), and Université Nangui Abrogoua (UNA)
Subjects: [PHYS.PHYS.PHYS-OPTICS]Physics [physics]/Physics [physics]/Optics [physics.optics], Computer science, business.industry, Polarimetry, Statistical and Nonlinear Physics, 02 engineering and technology, Full color, Polarizer, 021001 nanoscience & nanotechnology, Polarization (waves), 01 natural sciences, Atomic and Molecular Physics, and Optics, law.invention, 010309 optics, Optics, Optical microscope, law, Computer Science::Computer Vision and Pattern Recognition, 0103 physical sciences, [SPI.OPTI]Engineering Sciences [physics]/Optics / Photonic, Color imaging, 0210 nano-technology, business, Color coordinates
Abstract: International audience; Many anticounterfeiting tags rely on images intricate in different color and/or different polarization states to create optical effects invisible in conventional observation conditions. We build here an imaging micropolarimeter based on the dual rotating compensator system and using the color capabilities of cameras to yield the full polarimetric information for any color coordinates in one acquisition step. After correction for the camera response, the full color image reconstructed from the polarimetric response is validated by the comparison with images obtained in an optical microscope fitted with polarizers.
Published: 2021

43. Hyperspectral super-resolution accounting for spectral variability: LL1-based recovery and blind unmixing

Author: Prévost, Clémence, Borsoi, Ricardo, Usevich, Konstantin, Brie, David, Bermudez, José C. M., Richard, Cédric, Centre de Recherche en Automatique de Nancy (CRAN), Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Universidade Federal de Santa Catarina = Federal University of Santa Catarina [Florianópolis] (UFSC), Joseph Louis LAGRANGE (LAGRANGE), Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015 - 2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015 - 2019) (COMUE UCA)-Observatoire de la Côte d'Azur, Université Côte d'Azur (UCA)-COMUE Université Côte d'Azur (2015 - 2019) (COMUE UCA)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS), Centre National de la Recherche Scientifique (CNRS), and Catholic University of Pelotas (UCPEL)
Subjects: Hyperspectral super-resolution, hyperspectral unmixing, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Computer Science::Computer Vision and Pattern Recognition, spectral variability, tensor decompositions, image fusion
Abstract: In this paper, we propose to jointly solve the hyperspectral super-resolution and hyperspectral unmixing problems using a coupled LL1 block-tensor decomposition. We focus on the specific case of spectral variability occurring between the observed low-resolution images. Exact recovery conditions are provided. We propose two algorithms: an unconstrained one and another one subject to non-negativity constraints, to solve the problems at hand. We showcase performance of the proposed approach on a set of synthetic and semi-real images.
Published: 2021

44. Constrained feature selection for semisupervised color-texture image segmentation using spectral clustering

Author: Kamal Hammouche, Ludovic Macaire, Abderezak Salmi, Université Mouloud Mammeri [Tizi Ouzou] (UMMTO), Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (CRIStAL), and Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)
Subjects: Contextual image classification, business.industry, Computer science, Feature extraction, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Feature selection, Pattern recognition, Image segmentation, Atomic and Molecular Physics, and Optics, Spectral clustering, Computer Science Applications, Constraint (information theory), ComputingMethodologies_PATTERNRECOGNITION, Computer Science::Computer Vision and Pattern Recognition, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Segmentation, Pairwise comparison, Artificial intelligence, Electrical and Electronic Engineering, business, ComputingMilieux_MISCELLANEOUS
Abstract: Color-texture image segmentation remains a challenging problem due to extensive color-texture variability. Thus, the limited prior knowledge that is expressed by pairwise constraints can be exploited to guide the segmentation process. We propose a new semisupervised method by combining constrained feature selection and spectral clustering (SC) to perform color-texture image segmentation. The pairwise constraints are used by the constraint feature selection to choose the most relevant features among an available set of color and texture features. For this purpose, an innovative constraint score is developed to evaluate a subset of features at one time. A specific constrained SC algorithm involving the pairwise constraints is then applied to regroup the pixels into clusters. Experimental results on four benchmark datasets show that the proposed constraint score outperforms the main state-of-the-art constraint scores and that our semisupervised segmentation method is competitive compared with supervised, semisupervised, and unsupervised state-of-the-art segmentation methods.
Published: 2021

45. Segmentation géométrique du fouillis de mer dans des images de radar cohérents : Carte distance-doppler contre carte d'intensité distance-temps

Author: Jordan Michelet, Michel Berthier, Henry Chandran, Laurent Mascarilla, Mathématiques, Image et Applications - EA 3165 (MIA), Université de La Rochelle (ULR), and ERTE-ETSA (BOWEN group)
Subjects: Computer science, Aerospace Engineering, 02 engineering and technology, Sea state, symbols.namesake, Mathematical model, 0203 mechanical engineering, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Radar imaging, Clutter, [MATH.MATH-AP]Mathematics [math]/Analysis of PDEs [math.AP], Computer vision, Segmentation, 14. Life underwater, Electrical and Electronic Engineering, 020301 aerospace & aeronautics, Image segmentation, business.industry, Swell, Minimization, Computer Science::Computer Vision and Pattern Recognition, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], symbols, Noise (video), Artificial intelligence, Motion segmentation, business, Doppler effect, [MATH.MATH-NA]Mathematics [math]/Numerical Analysis [math.NA]
Abstract: International audience; This article aims at providing an efficient algorithm for sea clutter segmentation in coherent radar images. Using multiphase interface motion models, we show that segmentation in the range–time–intensity map gives much more relevant results than segmentation in the range–Doppler Map and avoids the use of assumptions on the clutter frequency response. Several mathematical models are evaluated on real data corresponding to Douglas sea states of approximately 5. Dealing with diffuse interface motion models involving more than two phases allows us to take into account the low contrast, the interference noise, and the contour weakness that are typical of range–time–intensity map images. Sea clutter segmentation allows us, for instance, to obtain oceanographic parameters such as sea state, direction, and velocity of the swell and the wind. It can also be seen as preprocessing that may be useful for target detection.; Cet article a pour but de fournir un algorithme efficace pour la segmentation du fouillis de mer dans les images radar cohérentes. En utilisant des modèles de mouvement d'interface à phase multiple, nous montrons que la segmentation dans la carte distance-temps-intensité donne des résultats beaucoup plus pertinents que la segmentation dans la carte distance-Doppler et évite l'utilisation d'hypothèses sur la réponse fréquentielle du fouillis. Plusieurs modèles mathématiques sont évalués sur des données réelles correspondant à des états de mer de Douglas d'environ 5. Le traitement de modèles de mouvement d'interface diffus impliquant plus que deux phases nous permet de prendre en compte le faible contraste, le bruit parasite et le manque de précision des contours qui sont typiques des images de la carte distance-temps-intensité. La segmentation du fouillis de mer nous permet, par exemple, d'obtenir des paramètres océanographiques tels que l'état de mer, la direction et la vitesse de la houle et du vent. Elle peut également être considérée comme un prétraitement qui peut être utile pour la détection de cibles.
Published: 2021

46. Imaging non-collinear antiferromagnetic textures via single spin relaxometry

Author: Vincent Cros, W. Akhtar, J.-P. Adam, S. Chouaieb, Karim Bouzehouane, Rana Tanos, Nicolas Reyren, Vincent Jacques, William Legrand, Florentin Fabre, Aurore Finco, Joo-Von Kim, Angela Haykal, Thibaut Devolder, Isabelle Robert-Philip, Fernando Ajejas, Laboratoire Charles Coulomb (L2C), Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS), Centre de Nanosciences et de Nanotechnologies (C2N), Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS), ANR-17-CE24-0025,TOPSKY,Propriétés topologiques des skyrmions magnétiques et opportunitiés pour le dévelopement de nouveaux dispositifs spintroniques(2017), European Project: 820394,ASTERIQs, European Project: 824123,SKYTOP, European Project: 866267,EXAFONIS, and European Project: 846597,DIMAF
Subjects: Relaxometry, Materials science, Science, FOS: Physical sciences, General Physics and Astronomy, 02 engineering and technology, Imaging techniques, 01 natural sciences, General Biochemistry, Genetics and Molecular Biology, Article, Magnetization, Spin wave, Magnetic properties and materials, Mesoscale and Nanoscale Physics (cond-mat.mes-hall), 0103 physical sciences, Antiferromagnetism, 010306 general physics, Spin-½, Magnonics, Multidisciplinary, Condensed matter physics, Spintronics, Condensed Matter - Mesoscale and Nanoscale Physics, Magnon, General Chemistry, 021001 nanoscience & nanotechnology, Computer Science::Computer Vision and Pattern Recognition, [PHYS.COND.CM-GEN]Physics [physics]/Condensed Matter [cond-mat]/Other [cond-mat.other], Condensed Matter::Strongly Correlated Electrons, 0210 nano-technology
Abstract: Antiferromagnetic materials are promising platforms for next-generation spintronics owing to their fast dynamics and high robustness against parasitic magnetic fields. However, nanoscale imaging of the magnetic order in such materials with zero net magnetization remains a major experimental challenge. Here we show that non-collinear antiferromagnetic spin textures can be imaged by probing the magnetic noise they locally produce via thermal populations of magnons. To this end, we perform nanoscale, all-optical relaxometry with a scanning quantum sensor based on a single nitrogen-vacancy (NV) defect in diamond. Magnetic noise is detected through an increase of the spin relaxation rate of the NV defect, which results in an overall reduction of its photoluminescence signal under continuous laser illumination. As a proof-of-concept, the efficiency of the method is demonstrated by imaging various spin textures in synthetic antiferromagnets, including domain walls, spin spirals and antiferromagnetic skyrmions. This imaging procedure could be extended to a large class of intrinsic antiferromagnets and opens up new opportunities for studying the physics of localized spin wave modes for magnonics., 7 pages, 5 figures
Published: 2021

47. Principal Component Analysis: A Generalized Gini Approach

Author: Charpentier, Arthur, Mussard, Stéphane, Ouraga, Tea, Détection, évaluation, gestion des risques CHROniques et éMErgents (CHROME) / Université de Nîmes (CHROME), Université de Nîmes (UNIMES), Centre de recherche en économie et management (CREM), Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Université de Caen Normandie (UNICAEN), Normandie Université (NU)-Normandie Université (NU), Université de Caen Normandie (UNICAEN), Normandie Université (NU)-Normandie Université (NU)-Université de Rennes (UR)-Centre National de la Recherche Scientifique (CNRS), Université du Québec à Montréal = University of Québec in Montréal (UQAM), Mussard, Stéphane, and Charpentier, Arthur
Subjects: Physics::Physics and Society, JEL: C - Mathematical and Quantitative Methods, PCA, [QFIN]Quantitative Finance [q-fin], [MATH] Mathematics [math], Astrophysics::Cosmology and Extragalactic Astrophysics, [QFIN] Quantitative Finance [q-fin], Computer Science::Multiagent Systems, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Computer Science::Computational Engineering, Finance, and Science, [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], Computer Science::Computer Vision and Pattern Recognition, Generalized Gini, [MATH]Mathematics [math], Robustness, [MATH.MATH-ST] Mathematics [math]/Statistics [math.ST], ComputingMilieux_MISCELLANEOUS
Abstract: A principal component analysis based on the generalized Gini correlation index is proposed (Gini PCA). The Gini PCA generalizes the standard PCA based on the variance. It is shown, in the Gaussian case, that the standard PCA is equivalent to the Gini PCA. It is also proven that the dimensionality reduction based on the generalized Gini correlation matrix, that relies on city-block distances, is robust to out-liers. Monte Carlo simulations and an application on cars data (with outliers) show the robustness of the Gini PCA and provide different interpretations of the results compared with the variance PCA.
Published: 2021

48. Sketched learning for image denoising

Author: Jean-François Aujol, Yann Traonmilin, Hui Shi, Institut de Mathématiques de Bordeaux (IMB), Université Bordeaux Segalen - Bordeaux 2-Université Sciences et Technologies - Bordeaux 1-Université de Bordeaux (UB)-Institut Polytechnique de Bordeaux (Bordeaux INP)-Centre National de la Recherche Scientifique (CNRS), and ANR-20-CE40-0001,EFFIREG,Régularisation performante de problèmes inverses en grande dimension pour le traitement de données(2020)
Subjects: Sketching, Rank (linear algebra), Computer science, business.industry, Noise reduction, Dimensionality reduction, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 020206 networking & telecommunications, Pattern recognition, 02 engineering and technology, Mixture model, Synthetic data, Image (mathematics), ComputingMethodologies_PATTERNRECOGNITION, Dimension (vector space), Computer Science::Computer Vision and Pattern Recognition, Image denoising, Machine learning, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Optimisation, Artificial intelligence, [MATH]Mathematics [math], business, Representation (mathematics)
Abstract: International audience; The Expected Patch Log-Likelihood algorithm (EPLL) and its extensions have shown good performances for image denoising. It estimates a Gaussian mixture model (GMM) from a training database of image patches and it uses the GMM as a prior for denoising. In this work, we adapt the sketching framework to carry out the compressive estimation of Gaussian mixture models with low rank covariances for image patches. With this method, we estimate models from a compressive representation of the training data with a learning cost that does not depend on the number of items in the database. Our method adds another dimension reduction technique (low-rank modeling of covariances) to the existing sketching methods in order to reduce the dimension of model parameters and to add flexibility to the modeling. We test our model on synthetic data and real large-scale data for patch-based image denoising. We show that we can produce denoising performance close to the models estimated from the original training database, opening the way for the study of denoising strategies using huge patch databases.
Published: 2021

49. Force Banner for the recognition of spatial relations

Author: Robin Deléarde, Laurent Wendling, Camille Kurtz, Philippe Dejean, Laboratoire d'Informatique Paris Descartes (LIPADE (URP_2517)), Université de Paris (UP), Magellium, and Magellium + Agence de l'Innovation de Défense (thèse CIFRE Défense)
Subjects: Similarity (geometry), Computer science, Scene understanding, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, 01 natural sciences, Convolutional neural network, Features and descriptors, Histogram, 0103 physical sciences, 0202 electrical engineering, electronic engineering, information engineering, 010306 general physics, Spatial analysis, Spatial organization, business.industry, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, Spatial relations, Object (computer science), Image processing and analysis, Spatial relation, Variable (computer science), Computer Science::Computer Vision and Pattern Recognition, 020201 artificial intelligence & image processing, Artificial intelligence, business
Abstract: International audience; Studying the spatial organization of objects in images is fundamental to increase both the understanding of a sensed scene and the explainability of the perceived similarity between images. This leads to the fundamental problem of handling spatial relations: given two objects depicted in an image, or two parts in an object, how to extract and describe efficiently their spatial configuration? Dedicated descriptors already exist for this task, like the efficient force histogram. In this article, we introduce the Force Banner, which extends it to two dimensions by using a panel of forces (attraction and repulsion), so as to benefit from more expressiveness and to model rich spatial information. This descriptor can be used as an intermediate representation of the image dedicated to the spatial configuration, and feed a classical 2D Convolutional Neural Network (CNN) to benefit from their powerful performances. As an illustration of this, we used it to solve a classification problem aiming to discriminate simple spatial relations, but with variable configuration complexities. Experimental results obtained on datasets of images with various shapes highlight the interest of this approach, in particular for complex spatial configurations.
Published: 2021

50. An Analysis and Implementation of the HDR+ Burst Denoising Method

Author: Julie Delon, Antoine Monod, Thomas Veit, Mathématiques Appliquées Paris 5 (MAP5 - UMR 8145), Institut National des Sciences Mathématiques et de leurs Interactions (INSMI)-Centre National de la Recherche Scientifique (CNRS)-Université de Paris (UP), and GoPro Technology France
Subjects: FOS: Computer and information sciences, I.4, Computer science, Computer Vision and Pattern Recognition (cs.CV), Noise reduction, Denoising algorithm, Computer Science - Computer Vision and Pattern Recognition, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, image signal processor, Image processing, Data_CODINGANDINFORMATIONTHEORY, Image (mathematics), motion estimation, F.2.1, temporal filtering, FOS: Electrical engineering, electronic engineering, information engineering, denoising, Computer vision, computer.programming_language, business.industry, burst denoising, Image restoration and reconstruction, Image and Video Processing (eess.IV), [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Maximization, Python (programming language), Electrical Engineering and Systems Science - Image and Video Processing, high dynamic range, Pipeline (software), Open source, Computer Science::Graphics, Computer Science::Computer Vision and Pattern Recognition, Signal Processing, computational photography, Artificial intelligence, business, computer, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Software
Abstract: HDR+ is an image processing pipeline presented by Google in 2016. At its core lies a denoising algorithm that uses a burst of raw images to produce a single higher quality image. Since it is designed as a versatile solution for smartphone cameras, it does not necessarily aim for the maximization of standard denoising metrics, but rather for the production of natural, visually pleasing images. In this article, we specifically discuss and analyze the HDR+ burst denoising algorithm architecture and the impact of its various parameters. With this publication, we provide an open source Python implementation of the algorithm, along with an interactive demo., 28 pages, 15 figures, published at https://doi.org/10.5201/ipol.2021.336, code on https://github.com/amonod/hdrplus-python
Published: 2021

Catalog

Books, media, physical & digital resources

See catalog results

Searchworks

Select search scope, currently: Articles Catalog books, media & more in Jio Institute collections Articles journal articles & other e-resources

Search

Search Constraints

Refine your results

Search Limiters

Topic

Publication Year Range

Language

Database

1,888 results on '"Computer Science::Computer Vision and Pattern Recognition"'

Search Results

Catalog

Select search scope, currently: Articles

Catalog

books, media & more in Jio Institute collections

Articles

journal articles & other e-resources