Search

Your search keyword '"Halim Benhabiles"' showing total 12 results
Start Over Author "Halim Benhabiles" Topic artificial intelligence
12 results on '"Halim Benhabiles"'

1. SuperpixelGridMasks Data Augmentation:Application to Precision Health and Other Real-world Data

Author

Karim Hammoudi, Adnane Cabani, Bouthaina Slika, Halim Benhabiles, Fadi Dornaika, Mahmoud Melkemi, Institut de Recherche en Informatique Mathématiques Automatique Signal - IRIMAS - UR 7499 [IRIMAS], École Supérieure d’Ingénieurs en Génie Électrique [ESIGELEC], Euskal Herriko Unibertsitatea [Guipúzcoa] [EHU], University of the Basque Country/Euskal Herriko Unibertsitatea [UPV/EHU], Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN], Bio-Micro-Electro-Mechanical Systems - IEMN [BIOMEMS - IEMN], JUNIA [JUNIA], Institut de Recherche en Informatique Mathématiques Automatique Signal - IRIMAS - UR 7499 (IRIMAS), Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA)), École Supérieure d’Ingénieurs en Génie Électrique (ESIGELEC), Euskal Herriko Unibertsitatea [Guipúzcoa] (EHU), Universidad del Pais Vasco / Euskal Herriko Unibertsitatea [Espagne] (UPV/EHU), University of the Basque Country/Euskal Herriko Unibertsitatea (UPV/EHU), Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 (IEMN), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-JUNIA (JUNIA), Université catholique de Lille (UCL)-Université catholique de Lille (UCL), Bio-Micro-Electro-Mechanical Systems - IEMN (BIOMEMS - IEMN), Université catholique de Lille (UCL)-Université catholique de Lille (UCL)-Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-JUNIA (JUNIA), JUNIA (JUNIA), and Université catholique de Lille (UCL)

Subjects
[SPI]Engineering Sciences [physics], Artificial Intelligence, Health Informatics, Computer Science Applications, Information Systems
Abstract

ressources projet: https://github.com/hammoudiproject/SuperpixelGridMasksdatasets used for the article: 1 Dataset Chest X-Ray Images: https://www.kaggle.com/datasets/paultimothymooney/chest-xray-pneumonia2 A PASCAL VOC dataset: http://host.robots.ox.ac.uk/pascal/VOC/databases.html#VOC2005_1; International audience; A novel approach of data augmentation based on irregular superpixel decomposition is proposed. This approach called SuperpixelGridMasks permits to extend original image datasets that are required by training stages of machine learning-related analysis architectures towards increasing their performances. Three variants named SuperpixelGridCut, SuperpixelGridMean, and SuperpixelGridMix are presented. These grid-based methods produce a new style of image transformations using the dropping and fusing of information. Extensive experiments using various image classification models as well as precision health and surrounding real-world datasets show that baseline performances can be significantly outperformed using our methods. The comparative study also shows that our methods can overpass the performances of other data augmentations. SuperpixelGridCut, SuperpixelGridMean, and SuperpixelGridMix codes are publicly available at https://github.com/hammoudiproject/SuperpixelGridMasks.

Published
2023
Full Text
View/download PDF

2. A CNN-based methodology for cow heat analysis from endoscopic images

Author

Agathe Decherf, Dominique Collard, Christophe Audebert, Ruiwen He, Abdelmalik Taleb-Ahmed, Feryal Windal, Halim Benhabiles, Gaël Even, Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 (IEMN), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-JUNIA (JUNIA), Université catholique de Lille (UCL)-Université catholique de Lille (UCL), Bio-Micro-Electro-Mechanical Systems - IEMN (BIOMEMS - IEMN), Université catholique de Lille (UCL)-Université catholique de Lille (UCL)-Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-JUNIA (JUNIA), JUNIA (JUNIA), Université catholique de Lille (UCL), Gènes Diffusion [Douai], Laboratory for Integrated Micro Mechatronics Systems (LIMMS), The University of Tokyo (UTokyo)-Centre National de la Recherche Scientifique (CNRS), COMmunications NUMériques - IEMN (COMNUM - IEMN), INSA Institut National des Sciences Appliquées Hauts-de-France (INSA Hauts-De-France), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 (IEMN), This project has been funded by the FEDER European program, JUNIA French Engineering school and Genes Diffusion French company., Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-JUNIA (JUNIA)-Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-JUNIA (JUNIA), Territoires, Environnement, Télédétection et Information Spatiale (UMR TETIS), and Centre de Coopération Internationale en Recherche Agronomique pour le Développement (Cirad)-AgroParisTech-Institut national de recherche en sciences et technologies pour l'environnement et l'agriculture (IRSTEA)

Subjects
Endoscopic image, Computer science, Machine vision, Context (language use), Artificial insemination, 02 engineering and technology, Machine learning, computer.software_genre, 030218 nuclear medicine & medical imaging, Upsampling, [SPI]Engineering Sciences [physics], 03 medical and health sciences, 0302 clinical medicine, Artificial Intelligence, 0202 electrical engineering, electronic engineering, information engineering, Android (operating system), Quantization (image processing), 2. Zero hunger, business.industry, Response time, Deep learning, Android CNN optimization, Software deployment, Cow heat, 020201 artificial intelligence & image processing, Artificial intelligence, State (computer science), business, computer
Abstract

International audience; In cattle farming, the artificial insemination technique is a biotechnology that brings to farmers a wide range of benefits namely health security, genetic gain and economic costs. The main condition for the success of artificial insemination within cattle is the heat (or estrus) detection. In this context, several cow heat detection systems have been recently proposed in the literature to assist the farmer in this task. Nevertheless, they are mainly based on the analysis of the physical behavior of the cow which may be affected by several factors related to its health and its environment. In this paper, we present a new vision system for cow heat detection which is based on the analysis of the genital tract of the cow. The main core of our system is a CNN model that has been designed and tailored for analyzing endoscopic images collected using an innovative insemination technology named Eye breed. The conducted experiments on two datasets namely our own dataset and a public dataset show the high accuracy of our CNN model (more than 97% for both datasets) outperforming 19 methods from the state of the art. Moreover, we propose an optimized version of our model for an Android deployment by exploiting several techniques namely quantization, GPU acceleration and video downsampling. The conducted tests on a smart-phone shows that our heat detection system has a response time of a few seconds.

Published
2021
Full Text
View/download PDF

3. MaskedFace-Net – A dataset of correctly/incorrectly masked face images in the context of COVID-19

Author

Karim Hammoudi, Adnane Cabani, Mahmoud Melkemi, Halim Benhabiles, Institut de Recherche en Systèmes Electroniques Embarqués (IRSEEM), Université de Rouen Normandie (UNIROUEN), Normandie Université (NU)-Normandie Université (NU)-École Supérieure d’Ingénieurs en Génie Électrique (ESIGELEC), Laboratoire International associé sur les phénomènes Critiques et Supercritiques en électronique fonctionnelle, acoustique et fluidique (LIA LICS/LEMAC), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF), Bio-Micro-Electro-Mechanical Systems - IEMN [BIOMEMS - IEMN], JUNIA [JUNIA], Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN], École Supérieure d’Ingénieurs en Génie Électrique [ESIGELEC], Institut de Recherche en Informatique Mathématiques Automatique Signal - IRIMAS - UR 7499 [IRIMAS], Bio-Micro-Electro-Mechanical Systems - IEMN (BIOMEMS - IEMN), Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 (IEMN), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-JUNIA (JUNIA)-Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-JUNIA (JUNIA), JUNIA (JUNIA), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-JUNIA (JUNIA), École Supérieure d’Ingénieurs en Génie Électrique (ESIGELEC), Institut de Recherche en Informatique Mathématiques Automatique Signal - IRIMAS - UR 7499 (IRIMAS), Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA)), Université de Strasbourg (UNISTRA), Université catholique de Lille (UCL)-Université catholique de Lille (UCL), Université catholique de Lille (UCL)-Université catholique de Lille (UCL)-Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-JUNIA (JUNIA), and Université catholique de Lille (UCL)

Subjects
FOS: Computer and information sciences, Masked face dataset, Smart health, 020205 medical informatics, Computer science, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, Medicine (miscellaneous), Health Informatics, Context (language use), 02 engineering and technology, Image editing, computer.software_genre, 01 natural sciences, Article, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Crowds, Health Information Management, FOS: Electrical engineering, electronic engineering, information engineering, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, 0202 electrical engineering, electronic engineering, information engineering, Net (polyhedron), Hardware_INTEGRATEDCIRCUITS, [INFO]Computer Science [cs], Face detection, ComputingMilieux_MISCELLANEOUS, Vulnerability (computing), Public health, business.industry, Feature matching, Deep learning, Image and Video Processing (eess.IV), 010401 analytical chemistry, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], COVID-19, Pattern recognition, Electrical Engineering and Systems Science - Image and Video Processing, 0104 chemical sciences, Computer Science Applications, Realistic image synthesis, Health education, Virus protection, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Face (geometry), Artificial intelligence, business, computer, Information Systems
Abstract

Wearing face masks appears as a solution for limiting the spread of COVID-19. In this context, efficient recognition systems are expected for checking that people faces are masked in regulated areas. Hence, a large dataset of masked faces is necessary for training deep learning models towards detecting people wearing masks and those not wearing masks. Currently, there are no available large dataset of masked face images that permits to check if faces are correctly masked or not. Indeed, many people are not correctly wearing their masks due to bad practices, bad behaviors or vulnerability of individuals (e.g., children, old people). For these reasons, several mask wearing campaigns intend to sensitize people about this problem and good practices. In this sense, this work proposes an image editing approach and three types of masked face detection dataset; namely, the Correctly Masked Face Dataset (CMFD), the Incorrectly Masked Face Dataset (IMFD) and their combination for the global masked face detection (MaskedFace-Net). Realistic masked face datasets are proposed with a twofold objective: i) detecting people having their faces masked or not masked, ii) detecting faces having their masks correctly worn or incorrectly worn (e.g.; at airport portals or in crowds). To the best of our knowledge, no large dataset of masked faces provides such a granularity of classification towards mask wearing analysis. Moreover, this work globally presents the applied mask-to-face deformable model for permitting the generation of other masked face images, notably with specific masks. Our datasets of masked faces (137,016 images) are available at https://github.com/cabani/MaskedFace-Net. The dataset of face images Flickr-Faces-HQ3 (FFHQ), publicly made available online by NVIDIA Corporation, has been used for generating MaskedFace-Net.

Published
2021
Full Text
View/download PDF

4. A generalized deep learning-based framework for assistance to the human malaria diagnosis from microscopic images

Author

Ziheng Yang, Karim Hammoudi, Ruiwen He, Feryal Windal, Halim Benhabiles, Dominique Collard, Department of Genetics, Evolution and Environment, University College of London [London] (UCL), Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 (IEMN), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-JUNIA (JUNIA), Université catholique de Lille (UCL)-Université catholique de Lille (UCL), JUNIA (JUNIA), Université catholique de Lille (UCL), Bio-Micro-Electro-Mechanical Systems - IEMN (BIOMEMS - IEMN), Université catholique de Lille (UCL)-Université catholique de Lille (UCL)-Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-JUNIA (JUNIA), Institut de Recherche en Informatique Mathématiques Automatique Signal (IRIMAS), Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA)), Laboratory for Integrated Micro Mechatronics Systems (LIMMS), The University of Tokyo (UTokyo)-Centre National de la Recherche Scientifique (CNRS), This project has received funding from the Interreg 2 Seas programme 2014-2020 co-funded by the European Regional Development Fund under subsidy contract No. 2S05-043 H4DC., and Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-JUNIA (JUNIA)-Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-JUNIA (JUNIA)

Subjects
Computer science, Machine learning, computer.software_genre, Plasmodium, World health, 03 medical and health sciences, [SPI]Engineering Sciences [physics], 0302 clinical medicine, Artificial Intelligence, parasitic diseases, medicine, Computational Science and Engineering, 030304 developmental biology, 0303 health sciences, biology, business.industry, Deep learning, Plasmodium parasite, biology.organism_classification, medicine.disease, 3. Good health, Blood smear, Infectious disease (medical specialty), 030220 oncology & carcinogenesis, Artificial intelligence, business, computer, Software, Malaria
Abstract

International audience; Malaria is an infectious disease caused by Plasmodium parasites and is potentially human life-threatening. Children under 5 years old are the most vulnerable group with approximately one death every two minutes, accounting for more than 65% of all malaria deaths. The World Health Organization (WHO) encourages the research of appropriate methods to treat malaria through rapid and economical diagnostic. In this paper, we present a deep learning-based framework for diagnosing human malaria infection from microscopic images of thin blood smears. The framework is based on a direct segmentation and classification approach which relies on the analysis of the parasite itself. The framework permits to segment the Plasmodium parasite in the images and to predict its species among four dominant classes: P. Falciparum, P. Malaria, P. Ovale, and P. Vivax. A high potential of generalization with a competitive performance of our framework on inter-class data is demonstrated through an experimental study considering several datasets. Our source code is publicly available on https://github.com/Benhabiles-JUNIA/MalariaNet.

Published
2021
Full Text
View/download PDF

5. Deep Learning based Detection of Hair Loss Levels from Facial Images

Author

Halim Benhabiles, Ignacio Arganda-Carreras, Feryal Windal, Karim Hammoudi, Fadi Dornaika, Ziheng Yang, and Mahmoud Melkemi

Subjects
Matching (statistics), Computer science, business.industry, Deep learning, Visibility (geometry), Context (language use), Pattern recognition, 02 engineering and technology, medicine.disease, 030207 dermatology & venereal diseases, 03 medical and health sciences, 0302 clinical medicine, Hair loss, Face (geometry), 0202 electrical engineering, electronic engineering, information engineering, medicine, 020201 artificial intelligence & image processing, Artificial intelligence, business
Abstract

Hair loss is a phenomenon known to affect people’s morale and self-confidence. Often, the awareness of the phenomenon and the possibilities of treatment is late. This paper investigates deep learning methods for detecting hairs loss levels by men from face images. In this context, a specific training dataset has been prepared with face images having varied levels of baldness. Moreover, in spite of the low visibility of hairs in such images, a matching method is proposed for automatically classifying facial images with respect to pattern classification tables of male baldness from the medical area. Experimental results show the potential and the efficiency for medical, security and commercial applications.

Published
2019
Full Text
View/download PDF

6. Image-based Ciphering of Video Streams and Object Recognition for Urban and Vehicular Surveillance Services

Author

Audrey Queudet, Safwan El Assad, Halim Benhabiles, Karim Hammoudi, Feryal Windal, Mohammed Abu Taha, Mahmoud Melkemi, Institut de Recherche en Informatique Mathématiques Automatique Signal (IRIMAS), Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA)), Palestine Polytechnic University (PPU), Institut Supérieur de l'Electronique et du Numérique - Lille (ISEN-Lille), Institut supérieur de l'électronique et du numérique (ISEN), Institut d'Électronique et des Technologies du numéRique (IETR), Université de Nantes (UN)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-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)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), Laboratoire des Sciences du Numérique de Nantes (LS2N), Université de Nantes - UFR des Sciences et des Techniques (UN UFR ST), Université de Nantes (UN)-Université de Nantes (UN)-École Centrale de Nantes (ECN)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Institut supérieur de l'électronique et du numérique (ISEN)-Université catholique de Lille (UCL), Université de Nantes (UN)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), Université de Nantes (UN)-Université de Nantes (UN)-École Centrale de Nantes (ECN)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), and Nantes Université (NU)-Université de Rennes 1 (UR1)

Subjects
[SPI.OTHER]Engineering Sciences [physics]/Other, Surveillance Systems, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Image Ci- phering, 050801 communication & media studies, 02 engineering and technology, Image Analysis, Image (mathematics), Remote computing, [SPI]Engineering Sciences [physics], 0508 media and communications, Image transfer, Server, 0202 electrical engineering, electronic engineering, information engineering, Computer vision, Pseudorandom number generator, Object Recognition, business.industry, 05 social sciences, Cognitive neuroscience of visual object recognition, Machine Learning, [SPI.TRON]Engineering Sciences [physics]/Electronics, Real-time Video Services, 020201 artificial intelligence & image processing, Artificial intelligence, business, Image based
Abstract

International audience; Nowadays, urban and vehicular surveillance systems are col-lecting large amounts of image data for feeding recognition systems e.g.towards proposing localization or navigation services. In many cases,these image data cannot directly be processed in situ by the acquisitionsystems in reason of their low computational capabilities. The acquiredimages are transferred to remote computing servers through various com-puter networks, then analyzed in details towards object recognition. Theobjective of this paper is twofold i) presenting image-based cypheringmethods that can eciently be applied for securing the image transferagainst consequences of image interceptions (e.g.; man-in-the-middle at-tacks) ii) presenting generic image-based analysis techniques that can beexploited for object recognition. Experimental results show end-to-endimage-based solutions for fostering developments of surveillance systemsand services in urban and vehicular environments.

Published
2019

7. A Comparative Study of 2 Resolution-Level LBP Descriptors and Compact Versions for Visual Analysis

Author

Oussama Taoufik, Feryal Windal, Karim Hammoudi, Mahmoud Melkemi, Fadi Dornaika, and Halim Benhabiles

Subjects
Local binary patterns, Computer science, business.industry, Computation, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Pattern recognition, Object (computer science), Image (mathematics), Set (abstract data type), Categorization, Computer Science::Computer Vision and Pattern Recognition, Artificial intelligence, business, Resolution (algebra)
Abstract

We describe computation methods of Local Binary Pattern (LBP) descriptors as well as of 2-Resolution-level LBP. Both classical and compact versions of these descriptors are illustrated and evaluated with image sets of varied natures. Each considered image set is associated to a contextual study case which has an applicative objective for visual analysis and object categorization. A comparative study shows performances and potentialities of each presented method.

Published
2018
Full Text
View/download PDF

8. Convolutional neural network for pottery retrieval

Author

Halim Benhabiles, Hedi Tabia, Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), and CY Cergy Paris Université (CY)-Centre National de la Recherche Scientifique (CNRS)-Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)

Subjects
Vocabulary, Computer science, media_common.quotation_subject, Speech recognition, Feature extraction, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Convolutional neural network, 3D object retrieval, 0202 electrical engineering, electronic engineering, information engineering, Visual Word, Electrical and Electronic Engineering, Image retrieval, media_common, Artificial neural network, business.industry, Vector quantization, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, Pattern recognition, Atomic and Molecular Physics, and Optics, Computer Science Applications, Bag-of-words model, 020201 artificial intelligence & image processing, Artificial intelligence, business, CNN
Abstract

International audience; The effectiveness of the convolutional neural network (CNN) has already been demonstrated in many challenging tasks of computer vision, such as image retrieval, action recognition, and object classification. This paper specifically exploits CNN to design local descriptors for content-based retrieval of complete or nearly complete three-dimensional (3-D) vessel replicas. Based on vector quantization, the designed descriptors are clustered to form a shape vocabulary. Then, each 3-D object is associated to a set of clusters (words) in that vocabulary. Finally, a weighted vector counting the occurrences of every word is computed. The reported experimental results on the 3-D pottery benchmark show the superior performance of the proposed method.

Published
2016
Full Text
View/download PDF

9. Learning Boundary Edges for 3D-Mesh Segmentation

Author

Mohamed Daoudi, Jean-Philippe Vandeborre, Guillaume Lavoué, Halim Benhabiles, Geometry Processing and Constrained Optimization (M2DisCo), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-École Centrale de Lyon (ECL), Université de Lyon-Université Lumière - Lyon 2 (UL2)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Université Lumière - Lyon 2 (UL2), FOX MIIRE (LIFL), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS), Institut TELECOM/TELECOM Lille1, Institut Mines-Télécom [Paris] (IMT), Université Lumière - Lyon 2 (UL2)-École Centrale de Lyon (ECL), Université de Lyon-Université de Lyon-Université Claude Bernard Lyon 1 (UCBL), 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)-Centre National de la Recherche Scientifique (CNRS)-Université Lumière - Lyon 2 (UL2)-École Centrale de Lyon (ECL), and Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Ground truth, evaluation, learning, business.industry, Computer science, 3D-mesh, segmentation, boundary edges, [INFO.INFO-MM]Computer Science [cs]/Multimedia [cs.MM], [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Scale-space segmentation, 020207 software engineering, 02 engineering and technology, Computer Graphics and Computer-Aided Design, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Segmentation, Polygon mesh, Computer vision, Artificial intelligence, ground-truth, business, Classifier (UML)
Abstract

International audience; This paper presents a 3D-mesh segmentation algorithm based on a learning approach. A large database of manually segmented 3D-meshes is used to learn a boundary edge function. The function is learned using a classifier which automatically selects from a pool of geometric features the most relevant ones to detect candidate boundary edges. We propose a processing pipeline that produces smooth closed boundaries using this edge function. This pipeline successively selects a set of candidate boundary contours, closes them and optimizes them using a snake movement. Our algorithm was evaluated quantitatively using two different segmentation benchmarks and was shown to outperform most recent algorithms from the state-of-the-art.

Published
2011
Full Text
View/download PDF

10. Belief-Function-Based Framework for Deformable 3D-Shape Retrieval

Author

Jean-Philippe Vandeborre, Hedi Tabia, and Halim Benhabiles

Subjects
Similarity (geometry), Geodesic, Heat kernel signature, business.industry, Active shape model, Feature extraction, Probability distribution, Pattern recognition, Function (mathematics), Artificial intelligence, Object (computer science), business, Mathematics
Abstract

The need for efficient tools to index and retrieve 3D content becomes even more acute. This paper presents a fully automatic 3D-object retrieval method. It consists of two main steps namely shape signature extraction to describe the shape of objects, and similarity computing to compute similarity between objects. In the first step (signature extraction), we use a shape descriptor called geodesic cords. This descriptor can be seen as a probability distribution sampled from a shape function. In the second step (similarity computing), a global distance, based on belief function theory, is computed between each pair wise of descriptors corresponding respectively to an object query and an object from a given database. Experiments on commonly-used benchmarks demonstrate that our method obtains competitive performance compared to 3D-object retrieval methods from the state-of-the-art.

Published
2014
Full Text
View/download PDF

11. Dynamic 3D Facial Expression Recognition Using Robust Shape Features

Author

Halim Benhabiles, Ahmed Maalej, and Hedi Tabia

Subjects
Facial expression, ComputingMethodologies_PATTERNRECOGNITION, Facial expression recognition, Geodesic, Computer science, business.industry, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Pattern recognition, Artificial intelligence, Hidden Markov model, business, Shape analysis (digital geometry)
Abstract

In this paper we present a novel approach for dynamic facial expression recognition based on 3D geometric facial features. Geodesic distances between corresponding 3D open curves are computed and used as features to describe the facial changes across sequences of 3D face scans. Hidden Markov Models (HMMs) are exploited to learn the curves shape variation through a 3D frame sequences, and the trained models are used to classify six prototypic facial expressions. Our approach shows high performance, and an overall recognition rate of 94.45% is attained after a validation on the BU-4DFE database.

Published
2013
Full Text
View/download PDF

12. A subjective experiment for 3D-mesh segmentation evaluation

Author

Halim Benhabiles, Jean-Philippe Vandeborre, Mohamed Daoudi, Guillaume Lavoué, FOX MIIRE (LIFL), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS), Geometry Processing and Constrained Optimization (M2DisCo), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-École Centrale de Lyon (ECL), Université de Lyon-Université Lumière - Lyon 2 (UL2)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Université Lumière - Lyon 2 (UL2), Institut TELECOM/TELECOM Lille1, Institut Mines-Télécom [Paris] (IMT), IEEE, ANR-07-MDCO-0015,MADRAS,3D Models And Dynamic models Representation And Segmentation(2007), Université Lumière - Lyon 2 (UL2)-École Centrale de Lyon (ECL), Université de Lyon-Université de Lyon-Université Claude Bernard Lyon 1 (UCBL), 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)-Centre National de la Recherche Scientifique (CNRS)-Université Lumière - Lyon 2 (UL2)-École Centrale de Lyon (ECL), and Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)

Subjects
evaluation, business.industry, Computer science, 3D-mesh, segmentation, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, Pattern recognition, 02 engineering and technology, Image segmentation, Benchmarking, Rendering (computer graphics), Mesh generation, 0202 electrical engineering, electronic engineering, information engineering, Automatic segmentation, 020201 artificial intelligence & image processing, Polygon mesh, Segmentation, Computer vision, Artificial intelligence, business, Subjective quality
Abstract

International audience; In this paper we present a subjective quality assessment experiment for 3D-mesh segmentation. For this end, we carefully designed a protocol with respect to several factors namely the rendering conditions, the possible interactions, the rating range, and the number of human subjects. To carry out the subjective experiment, more than 40 human observers have rated a set of 250 segmentation results issued from various algorithms. The obtained Mean Opinion Scores, which represent the human subjects' point of view toward the quality of each segmentation, have then been used to evaluate both the quality of automatic segmentation algorithms and the quality of similarity metrics used in recent mesh segmentation benchmarking systems.

Published
2010

Catalog

Books, media, physical & digital resources
See catalog results