Search

International audience; Texture characterization of photographic papers is likely to provide scholars with valuable information regarding artistic practices. Currently, texture assessment remains mostly based on visual and manual inspections, implying long repetitive tasks prone to inter- and even intra-observer variability. Automated texture characterization and classification procedures are thus important tasks in historical studies of large databases of photographic papers, likely to provide quantitative and reproducible assessments of texture matches. Such procedures may, for instance, produce vital information on photographic prints of uncertain origins. The hyperbolic wavelet transform, because it relies on the use of different dilation factor along the horizontal and vertical axes, permits to construct robust and meaningful multiscale and anisotropic representation of textures. In the present contribution, we explore how unsupervised clustering strategies can be complemented both to assess the significance of extracted clusters and the strength of the contribution of each texture to its associated cluster. Graph based filterbank strategies are notably investigated with the aim to produce small size significant clusters. These tools are illustrated at work on a large database of about 2500 exposed and non exposed photographic papers carefully assembled and documented by the MoMA and P. Messier's foundation. Results are commented and interpreted.

International audience; This paper investigates the classification of photographic paper tex-tures using visual descriptors. Such classification is called fine grain due to the very low inter-class variability. We propose a novel image representation for photographic paper texture categorization, relying on the incorporation of a powerful local descriptor into an efficient higher-order model deviation where texture is represented by com-puting statistics on the occurrences of specific local visual patterns. We perform an evaluation on two different challenging datasets of photographic paper textures and show such advanced methods in-deed outperforms existing descriptors.

A novel three-dimensional (3D) surface texture measure (3DSTM) is presented based on the micro-geometry of paper surfaces to classify different paper substrates. This is useful to automatically determine whether a document is printed on the correct paper substrate to help identify fraud. We use a 4-light source photometric stereo (PS) method to recover the dense 3D geometry of paper surfaces captured using a high-resolution sensing device. We derive a unique 3DSTM for each paper type based on the shape index (SI) map generated from the surface normals of the 3D data. We show that the proposed 3DSTM can robustly and accurately classify paper substrates with different physical properties and different surface textures. The accuracy of the proposed method is validated over a dataset comprising of 21 printed and 22 non-printed paper types and a measure of success over 92% is achieved.

// Xin Zhang 1, * , Lin-Feng Yan 1, * , Yu-Chuan Hu 1 , Gang Li 2 , Yang Yang 1 , Yu Han 1 , Ying-Zhi Sun 1 , Zhi-Cheng Liu 1 , Qiang Tian 1 , Zi-Yang Han 3 , Le-De Liu 3 , Bin-Quan Hu 3 , Zi-Yu Qiu 3 , Wen Wang 1 and Guang-Bin Cui 1 1 Department of Radiology, Tangdu Hospital, The Fourth Military Medical University, Xi’an 710038, Shaanxi, P.R. China 2 Department of Neurosurgery, Tangdu Hospital, The Fourth Military Medical University, Xi’an 710038, Shaanxi, P.R. China 3 Student Brigade, The Fourth Military Medical University, Xi’an 710032, Shaanxi, P.R. China * These authors have contributed equally to this work Correspondence to: Guang-Bin Cui, email: cgbtd@126.com Wen Wang, email: wangwen@fmmu.edu.cn Keywords: glioma grading, MRI, machine learning, attribute selection, support vector machine (SVM) Received: March 17, 2017 Accepted: April 19, 2017 Published: May 18, 2017 ABSTRACT Current machine learning techniques provide the opportunity to develop noninvasive and automated glioma grading tools, by utilizing quantitative parameters derived from multi-modal magnetic resonance imaging (MRI) data. However, the efficacies of different machine learning methods in glioma grading have not been investigated.A comprehensive comparison of varied machine learning methods in differentiating low-grade gliomas (LGGs) and high-grade gliomas (HGGs) as well as WHO grade II, III and IV gliomas based on multi-parametric MRI images was proposed in the current study. The parametric histogram and image texture attributes of 120 glioma patients were extracted from the perfusion, diffusion and permeability parametric maps of preoperative MRI. Then, 25 commonly used machine learning classifiers combined with 8 independent attribute selection methods were applied and evaluated using leave-one-out cross validation (LOOCV) strategy. Besides, the influences of parameter selection on the classifying performances were investigated. We found that support vector machine (SVM) exhibited superior performance to other classifiers. By combining all tumor attributes with synthetic minority over-sampling technique (SMOTE), the highest classifying accuracy of 0.945 or 0.961 for LGG and HGG or grade II, III and IV gliomas was achieved. Application of Recursive Feature Elimination (RFE) attribute selection strategy further improved the classifying accuracies. Besides, the performances of LibSVM, SMO, IBk classifiers were influenced by some key parameters such as kernel type , c , gama , K , etc. SVM is a promising tool in developing automated preoperative glioma grading system, especially when being combined with RFE strategy. Model parameters should be considered in glioma grading model optimization.

Image-guided liver surgery aims to enhance the precision of resection and ablation by providing fast localisation of tumours and adjacent complex vasculature to improve oncologic outcome. This Letter presents a novel end-to-end solution for fast stereo reconstruction and motion estimation that demonstrates high accuracy with phantom and clinical data. The authors' computationally efficient coarse-to-fine (CTF) stereo approach facilitates liver imaging by accounting for low texture regions, enabling precise three-dimensional (3D) boundary recovery through the use of adaptive windows and utilising a robust 3D motion estimator to reject spurious data. To the best of their knowledge, theirs is the only adaptive CTF matching approach to reconstruction and motion estimation that registers time series of reconstructions to a single key frame for registration to a volumetric computed tomography scan. The system is evaluated empirically in controlled laboratory experiments with a liver phantom and motorised stages for precise quantitative evaluation. Additional evaluation is provided through testing with patient data during liver resection.

International audience; Heterogeneous image segmentation is one of the most important tasks in image processing. It consists in partitioning the image into a set of disjoint regions. In this paper, we propose a new unsupervised image segmentation method that we call Unsupervised Image Segmentation (UIS). Our proposal performs an efficient image partition efficiently into primitive regions. This process is ensured by a local adaptive Kmeans and a novel centroids initialization. Then, similar sets are agglomerated to form homogeneous regions. For that, a low-level feature merging is employed according to a hierarchical linkage approach. Finally, in case of over-segmentation, appearing outlier regions are removed using a post process stage. Therefore, the UIS method allows to determine automatically the image region number. Indeed, it extends the Kmeans clustering to obtain meaningful regions. Several experiments were conducted using two heterogeneous image datasets. A comparison with well-known segmentation methods was also performed using the Liu's factor measure.

This paper presents a study on the potential of ultra-high accurate UAV-based 3D data capture by combining both imagery and LiDAR data. Our work is motivated by a project aiming at the monitoring of subsidence in an area of mixed use. Thus, it covers built-up regions in a village with a ship lock as the main object of interest as well as regions of agricultural use. In order to monitor potential subsidence in the order of 10 mm/year, we aim at sub-centimeter accuracies of the respective 3D point clouds. We show that hybrid georeferencing helps to increase the accuracy of the adjusted LiDAR point cloud by integrating results from photogrammetric block adjustment to improve the time-dependent trajectory corrections. As our main contribution, we demonstrate that joint orientation of laser scans and images in a hybrid adjustment framework significantly improves the relative and absolute height accuracies. By these means, accuracies corresponding to the GSD of the integrated imagery can be achieved. Image data can also help to enhance the LiDAR point clouds. As an example, integrating results from Multi-View Stereo potentially increases the point density from airborne LiDAR. Furthermore, image texture can support 3D point cloud classification. This semantic segmentation discussed in the final part of the paper is a prerequisite for further enhancement and analysis of the captured point cloud.

This paper presents a roughness analysis of sea surface from visible images by feature measurements of texture for the first time. The algorithms presented in this paper include six texture feature measurements of sea surface use gray level co-occurrence matrix, gray level-gradient co-occurrence matrix, Tamura texture feature, autocorrelation function, edge frequency and fractional Brownian motion autocorrelation. The empirical relationship between wind speeds (or sea surface roughness) and image texture roughness are estimated based on the extracted data. Our experiments have demonstrated that our texture methods and empirical relation between wind speeds and image texture roughness can potentially be used to analyze sea surface roughness from visible images.

The positioning accuracy of the gravity-aided navigation is closely related to the selection of local gravity maps. In this paper, the local gravity maps are converted into 8-bit gray images. The navigability features of the local gravity maps are extracted by using the image texture feature analysis methods, such as the gray histogram complexity, the Sobel operator, and the gray level co-occurrence matrix, and the navigability comprehensive evaluation of each local gravity map is obtained by using the projection pursuit model. According to the nebula model, a gravitation field algorithm is proposed. The gravitation field algorithm, genetic algorithm, and firefly algorithm are used to obtain the optimal projection direction of the projection pursuit model, respectively. We compared the optimizing results and gave the navigability evaluation of local gravity maps that provide the basis for the selection of local gravity map. The comparison results show that the gravitation field algorithm has the best performance in obtaining the optimal projection direction, and the contributions of the navigability features in the navigability evaluation are most equal. Under the same experimental conditions, the local gravity map selected by the method proposed in this paper has the highest positioning accuracy and the best matching track.

Crack extraction of solar panels has become a research focus in recent years. The cracks are small and hidden. In addition, there are particles of irregular shape and size on the surface of the polycrystalline solar panel, whose reflection position and direction are random. Therefore, there is a complex and uneven texture background on the solar panel image, which makes the crack extraction more difficult. In this paper, a crack extraction method combining image texture and morphological features is proposed. Firstly, the background texture and multi-scale details are suppressed by the linear filter and the Laplace pyramid decomposition method. Secondly, the edge can be extracted based on the modulus maximum method of the wavelet transform. Finally, cracks were extracted by using the improved Fuzzy C-means (FCM) clustering combining the morphological and texture features of the cracks. To make the extraction results more accurate and reasonable, an improved region growth algorithm is proposed to optimize the extraction results. All of the above research is closely centered on the accuracy and stability requirements of the solar cell crack detection, which is also the key point of this paper. The experimental results show that various improved or innovative algorithms proposed in this paper can accurately extract the position of cracks and obtain better extraction results. The detection results have good stability and can be faithful to the actual situation, which will promote the application of solar cells in more fields.

The texture image decomposition of porcelain fragments based on convolutional neural network is a functional algorithm based on energy minimization. It maps the image to a suitable space and can effectively decompose the image structure, texture, and noise. This paper conducts a systematic research on image decomposition based on variational method and compressed sensing reconstruction of convolutional neural network. This paper uses the layered variational image decomposition method to decompose the image into structural components and texture components and uses a compressed sensing algorithm based on hybrid basis to reconstruct the structure and texture components with large data. In compressed sensing, to further increase each feature component, the sparseness of tight framework wavelet-based shearlet transform is constructed and combined with wave atoms as a joint sparse dictionary big data. Under the condition of the same sampling rate, this algorithm can retain more image texture details and big data than the algorithm. The production of big data that meets the characteristics of the background text is actually an image-based normalization method. This method is not very sensitive to the relative position, density, spacing, and thickness of the text. A super-resolution model for certain texture features can improve the restoration effect of such texture images. And the dataset extracted by the classification method used in this paper accounts for 20% of the total dataset, and at the same time, the PSNR value of 0.1 is improved on average. Therefore, taking into account the requirements for future big data experimental training, this article mainly uses jpg/csv two standardized database datasets after segmentation. This dataset minimizes the difference between the same type of base text in the same period to lay the foundation for good big data recognition in the future.

This paper uses partial differential equation image processing techniques to establish image texture analysis models based on nonlinear anisotropic diffusion equations for image denoising, image segmentation, and image decomposition. This paper proposes a class of denoising models based on the hybrid anisotropic diffusion equation from the characteristics of different noise types. The model exhibits anisotropic diffusion near the image boundary, which can protect the boundary well, and isotropic diffusion inside the image; so, it can remove the noise effectively. We use the immovable point theory to prove the uniqueness of the model solution and further discuss other properties such as asymptotics of the solution. We propose a class of image texture analysis algorithms based on anisotropic diffusion equations and discrete gray level sets. First, a class of nonconvex generalized functions is proposed to remove the noise from the original image to obtain a smooth image while sharpening the edges. Then, an energy generalization function based on the gray level set is proposed, and the existence of the global minimum of this energy generalization function is discussed. Finally, an equivalent form of this energy generalization is given in the discrete case, and an image texture analysis algorithm is designed based on the equivalent form. The algorithm is improved by initial position optimization, dynamic adjustment of parameters, and adaptive selection of thresholds so that the ants can search along the real edges. Experiments show that the improved algorithm for image edge detection can obtain more complete edges and better detection results. The energy generalization function is calculated directly on the discrete gray level set instead of solving the corresponding partial differential equation, which can avoid the selection of the initial level set and the reinitialization of the level set, thus greatly improving the segmentation efficiency. The new algorithm has a high improvement in segmentation efficiency and can efficiently handle large size complex images.

This paper investigates the effect of anisotropic resolution on the image textural features of pharmacokinetic (PK) parameters of a murine glioma model using dynamic contrast-enhanced (DCE) MR images acquired with an isotropic resolution at 7T with pre-contrast T1 mapping. The PK parameter maps of whole tumors at isotropic resolution were generated using the two-compartment exchange model combined with the three-site-two-exchange model. The textural features of these isotropic images were compared with those of simulated, thick-slice, anisotropic images to assess the influence of anisotropic voxel resolution on the textural features of tumors. The isotropic images and parameter maps captured distributions of high pixel intensity that were absent in the corresponding anisotropic images with thick slices. A significant difference was observed in 33% of the histogram and textural features extracted from anisotropic images and parameter maps, compared to those extracted from corresponding isotropic images. Anisotropic images in different orthogonal orientations demonstrated 42.1% of the histogram and textural features to be significantly different from those of isotropic images. This study demonstrates that the anisotropy of voxel resolution needs to be carefully considered when comparing the textual features of tumor PK parameters and contrast-enhanced images.

Infrared and visible image fusion technology provides many benefits for human vision and computer image processing tasks, including enriched useful information and enhanced surveillance capabilities. However, existing fusion algorithms have faced a great challenge to effectively integrate visual features from complex source images. In this paper, we design a novel infrared and visible image fusion algorithm based on visual attention technology, in which a special visual attention system and a feature fusion strategy based on the saliency maps are proposed. Special visual attention system first utilizes the co-occurrence matrix to calculate the image texture complication, which can select a particular modality to compute a saliency map. Moreover, we improved the iterative operator of the original visual attention model (VAM), a fair competition mechanism is designed to ensure that the visual feature in detail regions can be extracted accurately. For the feature fusion strategy, we use the obtained saliency map to combine the visual attention features, and appropriately enhance the tiny features to ensure that the weak targets can be observed. Different from the general fusion algorithm, the proposed algorithm not only preserve the interesting region but also contain rich tiny details, which can improve the visual ability of human and computer. Moreover, experimental results in complicated ambient conditions show that the proposed algorithm in this paper outperforms state-of-the-art algorithms in both qualitative and quantitative evaluations, and this study can extend to the field of other-type image fusion.

This paper presents adaptive subspace-based inverse projections via division into multiple sub-problems (ASIP-DIMSs) for missing image data restoration. In the proposed method, a target problem for estimating missing image data is divided into multiple sub-problems, and each sub-problem is iteratively solved with the constraints of other known image data. By projection into a subspace model of image patches, the solution of each sub-problem is calculated, where we call this procedure “subspace-based inverse projection” for simplicity. The proposed method can use higher dimensional subspaces for finding unique solutions in each sub-problem, and successful restoration becomes feasible, since a high level of image representation performance can be preserved. This is the biggest contribution of this paper. Furthermore, the proposed method generates several subspaces from known training examples and enables derivation of a new criterion in the above framework to adaptively select the optimal subspace for each target patch. In this way, the proposed method realizes missing image data restoration using ASIP-DIMS. Since our method can estimate any kind of missing image data, its potential in two image restoration tasks, image inpainting and super-resolution, based on several methods for multivariate analysis is also shown in this paper.

Image texture is an important visual cue in image processing and analysis. Texture feature expression is an important task of geo-objects expression by using a high spatial resolution remote sensing image. Texture features based on gray level co-occurrence matrix (GLCM) are widely used in image spatial analysis where the spatial scale is especially of great significance. Based on the Fourier frequency-spectral analysis, this paper proposes an optimal scale selection method for GLCM. Different subset textures are firstly upscaled by GLCM with different window sizes. Then the multiscale texture feature images are converted into the frequency domain by Fourier transform. Consequently, the radial distribution and angular distribution curves changing with different window sizes from spectrum energy can be achieved, by which the texture window size can be selected. In order to verify the validity of this proposed texture scale selection method, this paper uses high-resolution fusion images to classify land cover based on multiscale texture expression. The results show that the proposed method combining frequency-spectral analysis-based texture scale selection can guarantee the quality and accuracy of the classification, which further proves the effectiveness of optimal texture window size selection method bases on frequency spectrum analysis. Other than scale selection in spatial domain, this paper casts a novel idea for texture scale selection in the frequency domain, which is meant for scale processing of remote sensing image.

Wireless capsule endoscopy (WCE) has revolutionised the diagnosis and treatment of gastrointestinal tract, especially the small intestine which is unreachable by traditional endoscopies. The drawback of the WCE is that it produces a large number of images to be inspected by the clinicians. Hence, the design of a computer-aided diagnosis (CAD) system will have a great potential to help reduce the diagnosis time and improve the detection accuracy. To address this problem, the authors propose a CAD system for automatic detection of ulcer in WCE images. Firstly, they enhance the input images to be better exploited in the main steps of the proposed method. Afterward, segmentation using saliency map-based texture and colour is applied to the WCE images in order to highlight ulcerous regions. Then, inspired by the existing feature extraction approaches, a new one has been proposed for the recognition of the segmented regions. Finally, a new recognition scheme is proposed based on hidden Markov model using the classification scores of the conventional methods (support vector machine, multilayer perceptron and random forest) as observations. Experimental results with two different datasets show that the proposed method gives promising results. This paper is a postprint of a paper submitted to and accepted for publication in [IET Image Processing] and is subject to Institution of Engineering and Technology Copyright. The copy of record is available at the IET Digital Library

Bioimage classification is increasingly becoming more important in many biological studies including those that require accurate cell phenotype recognition, subcellular localization, and histopathological classification. In this paper, we present a new General Purpose (GenP) bioimage classification method that can be applied to a large range of classification problems. The GenP system we propose is an ensemble that combines multiple texture features (both handcrafted and learned descriptors) for superior and generalizable discriminative power. Our ensemble obtains a boosting of performance by combining local features, dense sampling features, and deep learning features. Each descriptor is used to train a different Support Vector Machine that is then combined by sum rule. We evaluate our method on a diverse set of bioimage classification tasks each represented by a benchmark database, including some of those available in the IICBU 2008 database. Each bioimage classification task represents a typical subcellular, cellular, and tissue level classification problem. Our evaluation on these datasets demonstrates that the proposed GenP bioimage ensemble obtains state-of-the-art performance without any ad-hoc dataset tuning of the parameters (thereby avoiding any risk of overfitting/overtraining). To reproduce the experiments reported in this paper, the MATLAB code of all the descriptors is available at https://github.com/LorisNanni and https://www.dropbox.com/s/bguw035yrqz0pwp/ElencoCode.docx?dl=0.

With the rapid development of gymnastics technology, novel movements are also emerging. Due to the emergence of various complicated new movements, higher requirements are put forward for college gymnastics teaching. Therefore, it is necessary to combine the multimedia simulation technology to construct the human body rigid model and combine the image texture features to display the simulation image in texture form. In the study, GeBOD morphological database modeling was used to provide the data needed for the modeling of the whole-body human body of the joint and used for dynamics simulation. Simultaneously, in order to analyze and summarize the technical essentials of the innovative action, this experiment compared and analyzed the hem stage of the cross-headstand movement of the subject and the hem stage of the 180° movement. Research shows that the method proposed in this paper has certain practical effects.

Camouflage plays an indispensable role in modern military. Generally, a camouflage pattern includes a plurality of shapes units, which are split by elemental colors. The fixed camouflage pattern is low adaptability and concealability for changeable battlefields. Moreover, the conventionally camouflage design is time and resource consuming for manual drawing. In this paper, we propose a dynamic camouflage synthesizing method. Firstly, the texture patterns of one class of battlefield images is extracted using convolutional transfer network. We use 3*3 convolution kernels to extract texture features. And the covariance matrix is used as loss function to calculate the loss of different image texture features. Colors construction and their distribution of the specified battlefield images is extracted according to a clustering-based algorithm. Finally, the statistical color units are embedded into the texture patterns. We assess the adaptability and the concealability of synthesized camouflage using Eye Tracking based criteria. Comparing to the People’s Liberation Army Type 87 woodland pattern and the digital camouflage pattern synthesized using our previous method, testing results of our synthesized camouflage patterns were better in different saccade indicators. This demonstrates camouflage pattern synthesize proposed got better concealment and the validity of proposed method. Besides, we also compared our method with local binary pattern for extracting texture features. The experiments results indicated the method proposed had better consistency to the scene images.

Current steganalyzers based on deep learning mostly adopt wider or deeper designs to improve detection performance. However, an overly complex network increases the training cost and is not conducive to its expansion and optimization. Moreover, steganalysis pays more attention to high-frequency information corresponding to the image texture. However, the deeper the network, the more likely it is to learn low-frequency information corresponding to the image content, which is inconsistent with the goal of steganalysis. In response to these problems, a multi-frequency residual deep convolutional neural network for steganalysis of color images called MFRNet is proposed in this paper. We apply the idea of multi-frequency analysis to steganography detection for the first time, effectively controlling the network scale. By designing columns of different depths, it can learn different frequency components of steganographic noise at the same time. The detection performance is better than the existing networks that only learn a single frequency component of steganographic noise at the same depth. Therefore, it can achieve a good detection performance with a lighter architecture. In addition, by designing residual basic blocks with different residual shortcuts, different scales of steganographic noise residuals can be calculated at the same time, which can effectively suppress the interference of image content, so as to better reduce the impact of steganography algorithm mismatch and payload mismatch than the existing methods. The experimental results on PPG-LIRMM-COLOR showed that the proposed MFRNet outperformed the state-of-the-art model WISERNet.

The color and contrast of objects in the image will be affected by meteorological factors, especially rain and snow will block part of the image, which will change the information contained in the image. Image restoration under bad weather conditions has practical application value. At present, most of the research focuses on the removal of fog, and the research on complex rain and snow is relatively less. Rain has more prominent features in gradient domain, and it is more distinct from non-rain image texture. In this paper, Generative Adversarial Networks is used to combine the information of image in gradient domain and spatial domain to get better performance of rain removal. Gradient aided coding is used in the generator to generate depth features that are more conducive to rain removal. In the discriminator, the gradient is used as an additional input to provide more recognizable rain and non-rain information, which enhances the discriminator’s ability to distinguish the image generated by the generator and the ground truth. By modifying the network structure of the expanded spatial pyramid pooling (ASPP), the abnormal rain removal results produced by the generator are reduced. Experimental results show that the proposed method improves the performance of rain removal and the visual quality of the generated image.

Speckle noise reduction is an important area of research in the field of ultrasound image processing. Several algorithms for speckle noise characterization and analysis have been recently proposed in the area. Synthetic ultrasound images can play a key role in noise evaluation methods as they can be used to generate a variety of speckle noise models under different interpolation and sampling schemes, and can also provide valuable ground truth data for estimating the accuracy of the chosen methods. However, not much work has been done in the area of modelling synthetic ultrasound images, and in simulating speckle noise generation to get images that are as close as possible to real ultrasound images. An important aspect of simulated synthetic ultrasound images is the requirement for extensive quality assessment for ensuring that they have the texture characteristics and gray-tone features of real images. This paper presents texture feature analysis of synthetic ultrasound images using local binary patterns (LBP) and demonstrates the usefulness of a set of LBP features for image quality assessment. Experimental results presented in the paper clearly show how these features could provide an accurate quality metric that correlates very well with subjective evaluations performed by clinical experts.

Submission to Reconnaissance de Formes et Intelligence Artificielle (RFIA) 2014, France (2014) - Paper ID 16 / Paper ID114; [Résumé en français] Cet article présente une nouvelle approche appelée bag-of-bags of words (BBoW) pour la recherche d'images par le contenu (CBIR). Il s'agit d'une extension du modèle classique dit sac-de-mots (bag of words - BoW). Dans notre approche, une image est représentée par un graphe placé sur une grille régulière de pixels de l'image. Les poids sur les arêtes dépendent de caractéristiques locales de couleur. Le graphe est découpé en un nombre fixe de régions qui constituent une partition irrégulière de l'image par la méthode Normalized Cuts. Enfin, chaque partition est représentée par sa propre signature suivant le même schéma que le BoW. Une image est donc décrite par un ensemble de signatures qui sont ensuite combinées pour la recherche d'images similaires dans une base de données. Contrairement aux méthodes existantes telle que Spatial Pyramid Matching (SPM), le modèle BBoW proposé ne repose pas sur l'hypothèse que des parties similaires d'une scène apparaissent toujours au même endroit dans des images d'une même catégorie. L'extension de cette méthode à une approche multi-échelle, appelée Irregular Pyramid Matching (IPM), est également décrite. Les résultats démontrent la qualité de notre approche lorsque les partitions obtenues sont stables au sein d'une même catégorie d'images. Une analyse statistique est menée pour définir concrètement la notion de partition stable. Mots Clef : Recherche d'images par le contenu, coupe de graphes, Normalized Cuts, Sac de mots. [Abstract in English] This paper presents a novel approach, named bag-of-bags of words (BBoW), to address the problem of Content-Based Image Retrieval (CBIR) from image databases. The proposed bag-of-bags of words model extends the classical bag-of-words (BoW) model. An image is represented as a connected full graph of local features on a regular grid. Then irregular partitions (subgraphs) of images are further built via Normalized Cuts. Each subgraph in the partition is then represented by its own signature. Compared to existing methods for image retrieval, such as Spatial Pyramid Matching (SPM), the BBoW model does not assume that similar parts of a scene always appear at the same location in images of the same category. The extension of the proposed model to pyramid gives rise to a method we name irregular pyramid matching (IPM). The experiments demonstrate the strength of our method for image retrieval when the partitions are stable across an image category. The statistical analysis of subgraphs is discussed in the paper. Keywords : Content-based image retrieval, graph partitioning, Normalized Cuts, Bag of words.

Since the recent challenge that humanity is facing against COVID-19, several initiatives have been put forward with the goal of creating measures to help control the spread of the pandemic. In this paper we present a series of experiments using supervised learning models in order to perform an accurate classification on datasets consisting of medical images from COVID-19 patients and medical images of several other related diseases affecting the lungs. This work represents an initial experimentation using image texture feature descriptors, feed-forward and convolutional neural networks on newly created databases with COVID-19 images. The goal was setting a baseline for the future development of a system capable of automatically detecting the COVID-19 disease based on its manifestation on chest X-rays and computerized tomography images of the lungs.

In recent years, great progress has been made in the study of semantic segmentation in the field of computer vision. The accuracy of semantic segmentation has been constantly improved, and it has been widely applied in the fields of automatic driving, medical treatment and remote sensing image classification.Semantic segmentation in all kinds of neural network structure has been optimized, according to different segmentation task put forward different loss function and different optimization algorithm to improve the accuracy of classification, such as used in the classification task more softmax cross entropy loss in the sigmoid function is used in the classification task, two different loss functions have a different impact on classification results, at the same time, the training data set imbalance can also cause the precision of classification result deviation.In the task of remote sensing image classification, it is often necessary to extract and classify a variety of different land types, such as road, water system, vegetation, etc., from an image, but sometimes it is also necessary to extract one of the land types.Due to remote sensing image contains abundant spectral information, so the remote sensing image classification task is different from ordinary classification task scenarios, common softmax and sigmoid function, the number can not meet the existing remote sensing image classification task, this requires a combination of specific classification task to adjust and optimize the loss function, to adapt to the different classification task.As a major sugarcane planting province in China, guangxi plays an important role in the development of China's sugar industry. Therefore, it is of great significance to propose sugarcane planting area through high-resolution satellite remote sensing image.But because of guangxi planting condition is complicated and changeable weather condition, often appear cloudy, so in high resolution satellite remote sensing image acquisition and there is still a big challenge on extraction and classification, and on the high rate of satellite remote sensing image texture feature of sugarcane and cassava, corn and other crops of texture feature are similar, therefore in the process of classification will easy to misjudge corn, cassava as sugar cane, which led to a decline in classification accuracy.This paper combined with the extraction of sugarcane planting area based on high-resolution satellite remote sensing images by Jaccard loss of Lovasz hinge, and compared the effects of different loss functions on the accuracy of the results through experiments. Finally, it was concluded that combining Jaccard loss of Lovasz hinge could effectively reduce losses and improve the extraction accuracy of sugarcane planting area.

Tongue diagnosis is one of the important methods in the Chinese traditional medicine. Doctors can judge the disease’s situation by observing patient’s tongue color and texture. This paper presents a novel approach to extract color and texture features of tongue images. First, we use improved GLA (Generalized Lloyd Algorithm) to extract the main color of tongue image. Considering that the color feature cannot fully express tongue image information, the paper analyzes tongue edge’s texture features and proposes an algorithm to extract them. Then, we integrate the two features in retrieval by different weight. Experimental results show that the proposed method can improve the detection rate of lesion in tongue image relative to single feature retrieval.

Texture descriptors have an important role in recognizing face images. However, almost all the existing local texture descriptors use nearest neighbors to encode a texture pattern around a pixel. But in face images, most of the pixels have similar characteristics with that of its nearest neighbors because the skin covers large area in a face and the skin tone at neighboring regions are same. Therefore this paper presents a general framework called Local Texture Description Framework that uses only eight pixels which are at certain distance apart either circular or elliptical from the referenced pixel. Local texture description can be done using the foundation of any existing local texture descriptors. In this paper, the performance of the proposed framework is verified with three existing local texture descriptors Local Binary Pattern (LBP), Local Texture Pattern (LTP) and Local Tetra Patterns (LTrPs) for the five issues viz. facial expression, partial occlusion, illumination variation, pose variation and general recognition. Five benchmark databases JAFFE, Essex, Indian faces, AT&T and Georgia Tech are used for the experiments. Experimental results demonstrate that even with less number of patterns, the proposed framework could achieve higher recognition accuracy than that of their base models.

This paper presents a scientific foundation for automated stroke severity classification. We have constructed and assessed a system which extracts diagnostically relevant information from Magnetic Resonance Imaging (MRI) images. The design was based on 267 images that show the brain from individual subjects after stroke. They were labeled as either Lacunar Syndrome (LACS), Partial Anterior Circulation Syndrome (PACS), or Total Anterior Circulation Stroke (TACS). The labels indicate different physiological processes which manifest themselves in distinct image texture. The processing system was tasked with extracting texture information that could be used to classify a brain MRI image from a stroke survivor into either LACS, PACS, or TACS. We analyzed 6475 features that were obtained with Gray-Level Run Length Matrix (GLRLM), Higher Order Spectra (HOS), as well as a combination of Discrete Wavelet Transform (DWT) and Gray-Level Co-occurrence Matrix (GLCM) methods. The resulting features were ranked based on the p-value extracted with the Analysis Of Variance (ANOVA) algorithm. The ranked features were used to train and test four types of Support Vector Machine (SVM) classification algorithms according to the rules of 10-fold cross-validation. We found that SVM with Radial Basis Function (RBF) kernel achieves: Accuracy (ACC) = 93.62%, Specificity (SPE) = 95.91%, Sensitivity (SEN) = 92.44%, and Dice-score = 0.95. These results indicate that computer aided stroke severity diagnosis support is possible. Such systems might lead to progress in stroke diagnosis by enabling healthcare professionals to improve diagnosis and management of stroke patients with the same resources.

We would like to thank EPSRC impact acceleration fund (EP/K503940/1) for helping support this project. RR was supported as part of the James-Watt Scholarship during her PhD research at the Heriot-Watt University. Co-locating the gross tumour volume (GTV) on cone-beam computed tomography (CBCT) of non small cell lung cancer (NSCLC) patients receiving radiotherapy (RT) is difficult because of the lack of image contrast between the tumour and surrounding tissue. This paper presents a new image analysis approach, based on second-order statistics obtained from gray level co-occurrence matrices (GLCM) combined with level sets, for assisting clinicians in identifying the GTV on CBCT images. To demonstrate the potential of the approach planning CT images from 50 NSCLC patients were rigidly registered with CBCT images from fractions 1 and 10. Image texture analysis was combined with two level set methodologies and used to automatically identify the GTV on the registered CBCT images. The Dice correlation coefficients (μ± σ) calculated between the clinician-defined and image analysis defined GTV on the planning CT and the CBCT for three different parameterisations of the model were: 0.69 ± 0.19, 0.63 ± 0.17, 0.86 ± 0.13 on fraction 1 CBCT images and 0.70 ± 0.17, 0.62 ± 0.15, 0.86 ± 0.12 on fraction 10 CBCT images. This preliminary data suggests that the image analysis approach presented may have potential for clinicians in identifying the GTV in low contrast CBCT images of NSCLC patients. Additional validation and further work, particularly in overcoming the lack of gold standard reference images, are required to progress this approach. Postprint

Image segmentation is an essential and critical process in image processing and pattern recognition. In this paper we proposed a textured-based method to segment an input image into regions. In our method an entropy-based textured map of image is extracted, followed by an histogram equalization step to discriminate different regions. Then with the aim of eliminating unnecessary details and achieving more robustness against unwanted noises, a low-pass filtering technique is successfully used to smooth the image. As the next step, the appropriate pixons are extracted and delivered to a fuzzy c-mean clustering stage to obtain the final image segments. The results of applying the proposed method on several different images indicate its better performance in image segmentation compared to the other methods.

In land-use classification of hyperspectral remote sensing (RS) images, traditional classification methods often experience large amount of datasets and low efficiency. To solve these problems, a fast machine-learning method, the extreme learning machine (ELM) algorithm, was introduced. However, basic use of the ELM usually encounters problems of unstable classification results and low classification accuracy. Hence, in this paper, optimization methods for ELM-based RS image classification were mainly discussed and applied to solve the bottleneck problems. From the three perspectives of ensemble learning, making full use of image texture features, and deep learning, three classification optimization methods have been designed and implemented. The results show that: 1) To some extent, all the three methods can achieve a balance between classification accuracy and efficiency, i.e., they can maintain the advantage of ELM algorithm in classification efficiency and speed while have better classification accuracy; 2) The image texture feature optimization method (LBP-KELM) solves the problem of unsatisfactory classification results experienced by the ensemble learning optimization method (Ensemble-ELM) and further improves classification accuracy. However, the classification results are sensitive to the type of dataset; and 3) Fortunately, the optimization method combined with deep learning (CNN-ELM) can meet the application needs of multiple datasets. Furthermore, it can also further improve classification accuracy.

Color constancy is the capability to observe the true color of a scene from its image regardless of the scene's illuminant. It is a significant part of the digital image processing pipeline and is utilized when the true color of an object is required. Most existing color constancy methods assume a uniform illuminant across the whole scene of the image, which is not always the case. Hence, their performances are influenced by the presence of multiple light sources. This paper presents a color constancy adjustment technique that uses the texture of the image pixels to select pixels with sufficient color variation to be used for image color correction. The proposed technique applies a histogram-based algorithm to determine the appropriate number of segments to efficiently split the image into its key color variation areas. The K-means++ algorithm is then used to divide the input image into the pre-determined number of segments. The proposed algorithm identifies pixels with sufficient color variation in each segment using the entropies of the pixels, which represent the segment's texture. Then, the algorithm calculates the initial color constancy adjustment factors for each segment by applying an existing statistics-based color constancy algorithm on the selected pixels. Finally, the proposed method computes color adjustment factors per pixel within the image by fusing the initial color adjustment factors of all segments, which are regulated by the Euclidian distances of each pixel from the centers of gravity of the segments. The experimental results on benchmark single- and multiple-illuminant image datasets show that the images that are obtained using the proposed algorithm have significantly higher subjective and very competitive objective qualities compared to those that are obtained with the state-of-the-art techniques.

A classification algorithm based on LBP and local binary differential excitation pattern is presented for the classification of the crack and the linear mineral line on the surface of the birch veneer. The local binary differential excitation pattern (LB_DEP) is a texture description model proposed in this paper, which is generated by the combination of LBP and Weber's Law and describes the incidence relation between the image texture and the human visual perception. And the feature extracted by LB_DEP is expressed in a one-dimensional histogram. Then we establish a two-dimensional (2D) histogram constituted by the one-dimensional (1D) histogram of LBP and LB_DEP after being normalized and consolidated. Finally, the 2D histogram is used to classify the defects with Euclidean distance classifier. In addition, we establish an automatic optical inspection system for the birch ice cream bar. We also conduct the experiments with the images captured by the system. The results demonstrate that, compared with the state-of-the-art methods, our proposed algorithm can provide a better classification effect for the crack and the mineral line-the Recall, Precision and FNR are 0.930, 0.943 and 0.070 respectively. And the time consumption is 0.1416 s, which belongs to the millisecond level as with the compared methods.

In this paper, for evaluating the 3-D roughness of the additive manufacturing surfaces, we constructed a 3-D reconstruction system of structured light scanner. By calibrating the system, the center line of structured light is extracted online to reconstruct the profile of additive manufacturing and realize data registration. A dynamic texture coarseness algorithm is proposed, which combines 3-D data with 2-D Gaussian filtering and texture coarseness characteristics to transform 3-D roughness into visual image texture coarseness. The algorithm is applied to evaluate 3-D weld roughness with low delay. The validity of the algorithm is verified by roughness comparison specimens and the actual material adding experiment. The result of roughness is reliable and conforms to the evaluation standard of weld quality. At the same time, the position of structured light is optimized in the process of on-line detection, which reduces the complexity of extracting contour centerline and ensures the low delay characteristic of roughness calculation.

An image texture was defined in terms of pixel intensities and directionality. However, most of the current texture representation methods did not consider the two key factors simultaneously. To effectively capture the directional and pixel intensity information of texture, in this paper, we propose a novel and robust local descriptor, named locally directional and extremal pattern (LDEP), for texture classification. It extracts directional local difference count pattern (DLDCP) being made up of DLDCP in the odd positions and DLDCP in the even positions to express directional information in the local area in the first place. Furthermore, to acquire the extremum information remained by DLDCP, by concatenating extremum location pattern (ELP), extremum difference pattern (EDP), and extremum compression pattern (ECP) from the sampling points, we extract a neighbors extremum related local pattern (NERLP). The experimental results obtained from four representative texture databases (Prague, Stex, UIUC, Kth-tips2-a, Brodatz, and CUReT) demonstrate that our proposed LDEP descriptor can achieve comparable accurate classification rates in different conditions (rotation, illumination, scale variation, viewpoint variation, and noise) with ten typical texture classification methods.

The shortcoming of the coherence of digital holographic light sources leads to the generation of holographic reconstruction speckle noise, which seriously affects the quality of holographic reconstruction. Although many advanced algorithms for reducing speckle noise in digital holography (DH) have achieved good results, in the process of processing image speckle noise, the details of the image are blurred, and the information relating to the image texture is lost. Therefore, we propose a new algorithm, which combines automatic GrabCut and guided filtering to solve the problem of blurred image details in filtering reconstruction. The new algorithm is applied to the problem of holographic speckle removal for the first time. In this paper, the new algorithm not only achieves quasi-noise-free (approximate the noise-free state) DH reconstruction but also realizes the retention of details in the image. The quality of the resulting holographic reconstruction is comparable to that achieved by incoherent technology, which exceeds the current level of DH and produces a good visual effect.

Current TV image enhancement can be improved if the image is analyzed, objects of interest are segmented, and each segment is processed with content-specific enhancement algorithms. In this paper we present an algorithm for segmenting grass areas in video sequences. The system employs multi-scale texture analysis and adaptive color and position models for computing a pixel-based soft segmentation map. Compared to previously reported algorithms, our system shows a clear improvement in the detection result: at 10% false positive rate, the true positive rate of our algorithm yields 91%, vs. 66% and 58% of two existing methods.

Despite the breakthroughs in accuracy and speed of single image super-resolution using faster and deeper convolutional neural networks, one central problem remains largely unsolved: how do we recover the finer texture details when we super-resolve at large upscaling factors? The behavior of optimization-based super-resolution methods is principally driven by the choice of the objective function. Recent work has largely focused on minimizing the mean squared reconstruction error. The resulting estimates have high peak signal-to-noise ratios, but they are often lacking high-frequency details and are perceptually unsatisfying in the sense that they fail to match the fidelity expected at the higher resolution. In this paper, we present SRGAN, a generative adversarial network (GAN) for image super-resolution (SR). To our knowledge, it is the first framework capable of inferring photo-realistic natural images for 4x upscaling factors. To achieve this, we propose a perceptual loss function which consists of an adversarial loss and a content loss. The adversarial loss pushes our solution to the natural image manifold using a discriminator network that is trained to differentiate between the super-resolved images and original photo-realistic images. In addition, we use a content loss motivated by perceptual similarity instead of similarity in pixel space. Our deep residual network is able to recover photo-realistic textures from heavily downsampled images on public benchmarks. An extensive mean-opinion-score (MOS) test shows hugely significant gains in perceptual quality using SRGAN. The MOS scores obtained with SRGAN are closer to those of the original high-resolution images than to those obtained with any state-of-the-art method., 19 pages, 15 figures, 2 tables, accepted for oral presentation at CVPR, main paper + some supplementary material

Peer-reviewed paper presented at IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2016, Las Vegas, United States.; International audience; This paper presents a novel unsupervised method to transfer the style of an example image to a source image. The complex notion of image style is here considered as a local texture transfer, eventually coupled with a global color transfer. For the local texture transfer, we propose a new patch-based method based on an adaptive partition that captures the style of the example image and preserves the structure of the source image. More precisely, this example-based partition predicts how well a source patch matches an example patch. Results on various images show that out method outperforms the most recent techniques.

A patch-based noise level estimation algorithm is proposed in this paper, with patches generated from a single noisy image. One can easily estimate the noise level from image patches using principal component analysis (PCA) if the image comprises only weak textured patches. The challenge for patch-based noise level estimation is how to select weak textured patches from a noisy image. As described in this paper, we propose a novel algorithm to select weak textured patches from a single noisy image based on the gradients of the patches and their statistics. Then we estimate the noise level from the selected weak textured patches using PCA. We demonstrate experimentally that the proposed noise level estimation algorithm outperforms the state-of-the-art algorithm.

Recently developed spatial and spatio-temporal model checking techniques have a wide range of application domains, among which large scale distributed systems as well as signal and image analysis. In the latter domain, automatic and semi-automatic contouring in Medical Imaging has shown to be a very promising and versatile application that may facilitate the work of professionals in this domain, while supporting explainability, easy replicability and exchange of medical image analysis methods. In recent work, spatial model-checking has been applied to the 3D contouring of brain tumours and related oedema in magnetic resonance images of the brain. In the present paper we address the contouring of 2D images of nevi. One of the challenges of contouring nevi is that they show considerable inhomogeneity in shape, colour, texture and size. In addition these images often include also extraneous elements such as hairs, patches and rulers. To deal with this challenge we explore the use of a texture similarity operator in combination with spatial logic operators. We investigate the feasibility of our technique on images of a large public database. We compare the results with associated ground truth segmentation provided by domain experts; the results are very promising, both from the quality and from the performance point of view.

The rendering effect of known visual image texture is poor and the output image is not always clear. To solve this problem, this paper proposes a visual image rendering based on scene visual understanding algorithm. In this approach, the color segmentation of known visual scene is carried out according to a predefined threshold, and the segmented image is processed by morphology. For this purpose, the extraction rules are formulated to screen the candidate regions. The color image is fused and filtered in the neighborhood, the pixels of the image are extracted, and the 2D texture recognition is realized by multilevel fusion and visual feature reconstruction. Using compact sampling to extract more target features, feature points are matched, the coordinate system of known image information are integrated into a unified coordinate system, and design images are generated to complete art-aided design. Simulation results show that the proposed method is more accurate than the original method for extracting the information of known images, which helps to solve the problem of clearly visible output images and improves the overall design effect.

Existing inpainting methods have achieved promising performance in recovering defective images of specific scenes. However, filling holes involving multiple semantic categories remains challenging due to the obscure se-mantic boundaries and the mixture of different semantic textures. In this paper, we introduce coherence priors between the semantics and textures which make it possible to concentrate on completing separate textures in a semantic-wise manner. Specifically, we adopt a multi-scale joint optimization framework to first model the coherence priors and then accordingly interleaving optimize image inpainting and semantic segmentation in a coarse-to-fine manner. A Semantic-Wise Attention Propagation (SWAP) module is devised to refine completed image textures across scales by exploring non-local semantic coherence, which effectively mitigates the mix-up of textures. We also propose two coherence losses to constrain the consistency between the semantics and the inpainted image in terms of the overall structure and detailed textures. Experimental results demonstrate the superiority of our proposed method for challenging cases with complex holes.

International audience; In computer vision, reflection is a long-standing problem, it covers image textures, makes original color difficult to recognize, complicates the understanding of the scene. Most of the time, it is considered as “noise”. Many methods are proposed in order to reduce or delete the reflection effects in the image, but generally, the performances are not quite satisfactory. While instead of working on “de-noising”, we propose a method to take advantage of moving reflections that can be used for different computer vision applications. For instance, the segmentation of reflective manufactured objects is presented in this paper. We focus on tracking reflection components and segmenting continuous surfaces of the object by taking motion information into account. In this paper, a comparison with several conventional segmentation methods is proposed to illustrate how our approach significantly improves the segmentation results.

This paper presents a novel image fusion algorithm for a visible image and a near infrared (NIR) image. For the proposed fusion, the image is selected pixel-by-pixel based on local saliency. In this paper, the local saliency is measured by a local contrast. Then, the gradient information is fused and the output image is constructed by a Poisson image editing which preserves the gradient information of both images. The effectiveness of the proposed fusion algorithm is demonstrated in various applications including denoising, dehazing, and image enhancement.

Generative Adversarial Networks (GANs) can generate realistic fake face images that can easily fool human beings.On the contrary, a common Convolutional Neural Network(CNN) discriminator can achieve more than 99.9% accuracyin discerning fake/real images. In this paper, we conduct an empirical study on fake/real faces, and have two important observations: firstly, the texture of fake faces is substantially different from real ones; secondly, global texture statistics are more robust to image editing and transferable to fake faces from different GANs and datasets. Motivated by the above observations, we propose a new architecture coined as Gram-Net, which leverages global image texture representations for robust fake image detection. Experimental results on several datasets demonstrate that our Gram-Net outperforms existing approaches. Especially, our Gram-Netis more robust to image editings, e.g. down-sampling, JPEG compression, blur, and noise. More importantly, our Gram-Net generalizes significantly better in detecting fake faces from GAN models not seen in the training phase and can perform decently in detecting fake natural images.

International audience; The importance of image compression is now essential during transmission or storage processes in various data applications, especially in medical and biometric systems. To perform the effectiveness of the compression process on images and evaluate degradation caused by this process, image quality assessment becomes an important tool in image services. We note that the objective criteria in image quality depend especially on the image type and image texture composition. The actual tendency is to find metrics making better qualification on errors in compressed images and correlate with the human visual system. This paper presents an investigation to examine and evaluate image compression degradation by the use of a new tendency concept of image quality assessment based on texture and edge analysis. To perform and practice this evaluation, we compress the medical and biometric images using second-generation wavelet compression algorithms and study the degradation of texture information in these images.

The extraction of river planforms from remotely sensed satellite images is a task of crucial importance to many applications such as land planning, water resource monitoring or flood prediction. In this paper we present a novel framework for the extraction of rivers from Synthetic Aperture Radar (SAR) images, based on superpixel segmentation and subsequent classification. Superpixel segmentation is achieved via a modelling of the image pixels’ amplitudes and spatial coordinates as a finite mixture model, where the Generalised Gamma distribution is used to accurately model a variety of high-resolution SAR scenes. A number of features describing texture and statistics are extracted on a superpixel level, facilitating the identification of river superpixels - planforms are then extracted via unsupervised,agglomerative clustering thus eliminating the need for labelled training data. We present results of our proposed method on ICEYE-X2 and SENTINEL-1 SAR data demonstrating its ability to produce pixel-accurate river masks.

International audience; Several human being traits can be used as a robust and distinctive identifier for a given person. The palm region of the hand is one of these features that researchers in biometric fields have given a huge consideration in recent years. Many works have been proposed in the literature to design palmprint (an image acquired of the palm region) recognition framework. Extraction of prominent image local features is a critical module in most of these approaches. Local Binary Patterns (LBP) like methods, have emerged as one of the most effective feature extraction techniques. Despite a period of remarkable evolution, neither extensive and comprehensive evaluation nor comparison has been performed to date on a large number of LBP variants and non-LBP texture methods in palmprint recognition problem. Motivated by this, this paper aims to fill that gap and provide a comprehensive comparative study of the performance of a large number of recent texture descriptors in palmprint recognition. Extensive experimental results on the well-known constrained and unconstrained challenging palmprint databases, indicate that a number of tested local texture descriptors, which are evaluated for the first time on palmprint recognition, achieve promising results. Classification results are statistically compared through Wilcoxon signed rank test.