0000000001172982
AUTHOR
Désiré Sidibé
Visual saliency detection in colour images based on density estimation
International audience; A simple and effective method for visual saliency detection in colour images is presented. The method is based on the common observation that local salient regions exhibit distinct geometric and and texture patterns from neighbouring regions. We model the colour distribution of local image patches with a Gaussian density and measure the saliency of each patch as the statistical distance from that density. Experimental results with public datasets and comparison with other state-of-the-art methods show the effectiveness of our method.
Étude d'un système de stéréo-vision hybride
National audience; On considère dans ce travail un système de vision hybride fixe composé d'une caméra fisheye et d'une caméra PTZ dans un environnement rigide. Nous souhaitons être en mesure d'orienter la caméra mécanisée sur une cible visible depuis l'image omnidirectionnelle de manière à obtenir une image de bonne définition de l'objet d'intérêt à partir de la caméra PTZ. Nous proposons dans cet article d'utiliser la modélisation sphérique des images ainsi que les propriétés de la géométrie épipolaire afin d'initialiser la localisation de la cible dans la caméra PTZ.
Self-calibration of a PTZ Camera Using New LMI Constraints
In this paper, we propose a very reliable and flexible method for self-calibrating rotating and zooming cameras - generally referred to as PTZ (Pan-Tilt-Zoom) cameras. The proposed method employs a Linear Matrix Inequality (LMI) resolution approach and allows extra tunable constraints on the intrinsic parameters to be taken into account during the process of estimating these parameters. Furthermore, the considered constraints are simultaneously enforced in all views rather than in a single reference view. The results of our experiments show that the proposed approach allows for significant improvement in terms of accuracy and robustness when compared against state of the art methods.
On Spatio-Temporal Saliency Detection in Videos using Multilinear PCA
International audience; Visual saliency is an attention mechanism which helps to focus on regions of interest instead of processing the whole image or video data. Detecting salient objects in still images has been widely addressed in literature with several formulations and methods. However, visual saliency detection in videos has attracted little attention, although motion information is an important aspect of visual perception. A common approach for obtaining a spatio-temporal saliency map is to combine a static saliency map and a dynamic saliency map. In this paper, we extend a recent saliency detection approach based on principal component analysis (PCA) which have shwon good results wh…
Real-Time Human Pose Estimation from Body-Scanned Point Clouds
International audience; This paper presents a novel approach to estimate the human pose from a body-scanned point cloud. To do so, a predefined skeleton model is first initialized according to both the skeleton base point and its torso limb obtained by Principal Component Analysis (PCA). Then, the body parts are iteratively clustered and the skeleton limb fitting is performed, based on Expectation Maximization (EM). The human pose is given by the location of each skeletal node in the fitted skeleton model. Experimental results show the ability of the method to estimate the human pose from multiple point cloud video sequences representing the external surface of a scanned human body; being r…
Incorporating depth information into few-shot semantic segmentation
International audience; Few-shot segmentation presents a significant challengefor semantic scene understanding under limited supervision.Namely, this task targets at generalizing the segmentationability of the model to new categories given a few samples.In order to obtain complete scene information, we extend theRGB-centric methods to take advantage of complementary depthinformation. In this paper, we propose a two-stream deep neuralnetwork based on metric learning. Our method, known as RDNet,learns class-specific prototype representations within RGB anddepth embedding spaces, respectively. The learned prototypesprovide effective semantic guidance on the corresponding RGBand depth query ima…
Color and Flow Based Superpixels for 3D Geometry Respecting Meshing
We present an adaptive weight based superpixel segmentation method for the goal of creating mesh representation that respects the 3D scene structure. We propose a new fusion framework which employs both dense optical flow and color images to compute the probability of boundaries. The main contribution of this work is that we introduce a new color and optical flow pixel-wise weighting model that takes into account the non-linear error distribution of the depth estimation from optical flow. Experiments show that our method is better than the other state-of-art methods in terms of smaller error in the final produced mesh.
A supervised learning framework of statistical shape and probability priors for automatic prostate segmentation in ultrasound images
Prostate segmentation aids in prostate volume estimation, multi-modal image registration, and to create patient specific anatomical models for surgical planning and image guided biopsies. However, manual segmentation is time consuming and suffers from inter-and intra-observer variabilities. Low contrast images of trans rectal ultrasound and presence of imaging artifacts like speckle, micro-calcifications, and shadow regions hinder computer aided automatic or semi-automatic prostate segmentation. In this paper, we propose a prostate segmentation approach based on building multiple mean parametric models derived from principal component analysis of shape and posterior probabilities in a multi…
A Survey of Prostate Segmentation Methodologies in Ultrasound, Magnetic Resonance and Computed Tomography Images
Prostate segmentation is a challenging task, and the challenges significantly differ from one imaging modality to another. Low contrast, speckle, micro-calcifications and imaging artifacts like shadow poses serious challenges to accurate prostate segmentation in transrectal ultrasound (TRUS) images. However in magnetic resonance (MR) images, superior soft tissue contrast highlights large variability in shape, size and texture information inside the prostate. In contrast poor soft tissue contrast between prostate and surrounding tissues in computed tomography (CT) images pose a challenge in accurate prostate segmentation. This article reviews the methods developed for prostate gland segmenta…
An SVD-Based Approach for Ghost Detection and Removal in High Dynamic Range Images
International audience; In this paper, we propose a simple method for the ghost detection problem in the context of merging multiple low dynamic range (LDR) images to form a high dynamic range (HDR) image. We show that the second biggest singular values extracted over local spatio-temporal neighbourhoods can be effectively used for ghost region detection. Furthermore, we combine the proposed method with an exposure fusion technique to generate final HDR image free of ghosting artefacts. We present experimental results to illustrate the efficiency of the proposed method and quantitative comparison with other existing approaches show the good performance of our method in detecting and removin…
Classification of SD-OCT Volumes for DME Detection: An Anomaly Detection Approach
International audience; Diabetic Macular Edema (DME) is the leading cause of blindness amongst diabetic patients worldwide. It is characterized by accumulation of water molecules in the macula leading to swelling. Early detection of the disease helps prevent further loss of vision. Naturally, automated detection of DME from Optical Coherence Tomography (OCT) volumes plays a key role. To this end, a pipeline for detecting DME diseases in OCT volumes is proposed in this paper. The method is based on anomaly detection using Gaussian Mixture Model (GMM). It starts with pre-processing the B-scans by resizing, flattening, filtering and extracting features from them. Both intensity and Local Binar…
Classification of SD-OCT Volumes Using Local Binary Patterns: Experimental Validation for DME Detection
International audience; This paper addresses the problem of automatic classification of Spectral Domain OCT (SD-OCT) data for automatic identification of patients with Diabetic Macular Edema (DME) versus normal subjects. Optical Coherence Tomography (OCT) has been a valuable diagnostic tool for DME, which is among the most common causes of irreversible vision loss in individuals with diabetes. Here, a classification framework with five distinctive steps is proposed and we present an extensive study of each step. Our method considers combination of various pre-processings in conjunction with Local Binary Patterns (LBP) features and different mapping strategies. Using linear and non-linear cl…
Weighted Likelihood Function of Multiple Statistical Parameters to Retrieve 2D TRUS-MR Slice Correspondece for Prostate Biopsy
International audience; This paper presents a novel method to identify the 2D axial Magnetic Resonance (MR) slice from a pre-acquired MR prostate volume that closely corresponds to the 2D axial Transrectal Ultrasound (TRUS) slice obtained during prostate biopsy. The shape-context representations of the segmented prostate contours in both the imaging modalities are used to establish point correspondences using Bhattacharyya distance. Thereafter, Chi-square distance is used to find the prostate shape similarities between the MR slices and the TRUS slice. Normalized mutual information and correlation coefficient between the TRUS and MR slices are computed to find the information theoretic simi…
A Performance Evaluation of Fusion Techniques for Spatio-Temporal Saliency Detection in Dynamic Scenes
International audience; Visual saliency is an important research topic in computer vision applications, which helps to focus on regions of interest instead of processing the whole image. Detecting visual saliency in still images has been widely addressed in literature. However, visual saliency detection in videos is more complicated due to additional temporal information. A spatio-temporal saliency map is usually obtained by the fusion of a static saliency map and a dynamic saliency map. The way both maps are fused plays a critical role in the accuracy of the spatio-temporal saliency map. In this paper, we evaluate the performances of different fusion techniques on a large and diverse datas…
Apprentissage de modalités auxiliaires pour la localisation basée vision
In this paper we present a new training with side modality framework to enhance image-based localization. In order to learn side modality information, we train a fully convo-lutional decoder network that transfers meaningful information from one modality to another. We validate our approach on a challenging urban dataset. Experiments show that our system is able to enhance a purely image-based system by properly learning appearance of a side modality. Compared to state-of-the-art methods, the proposed network is lighter and faster to train, while producing comparable results.
Spectral clustering of shape and probability prior models for automatic prostate segmentation.
Imaging artifacts in Transrectal Ultrasound (TRUS) images and inter-patient variations in prostate shape and size challenge computer-aided automatic or semi-automatic segmentation of the prostate. In this paper, we propose to use multiple mean parametric models derived from principal component analysis (PCA) of shape and posterior probability information to segment the prostate. In contrast to traditional statistical models of shape and intensity priors, we use posterior probability of the prostate region determined from random forest classification to build, initialize and propagate our model. Multiple mean models derived from spectral clustering of combined shape and appearance parameters…
Tracking Moving Objects With a Catadioptric Sensor Using Particle Filter
International audience; Visual tracking in video sequences is a widely developed topic in computer vision applications. However, the emergence of panoramic vision using catadioptric sensors has created the need for new approaches in order to track an object in this type of images. Indeed the non-linear resolution and the geometric distortions due to the insertion of the mirror, make tracking in catadioptric images a very challenging task. This paper describes particle filter for tracking moving object over time using a catadioptric sensor. In this work different problems due to the specificities of the catadioptric systems such as geometry are considered. The obtained results demonstrate an…
Efficient Skin Detection under Severe Illumination Changes and Shadows
International audience; This paper presents an efficient method for human skin color detection with a mobile platform. The proposed method is based on modeling the skin distribution in a log-chromaticity color space which shows good invariance properties to changing illumination. The method is easy to implement and can cope with the requirements of real-world tasks such as illumination variations, shadows and moving camera. Extensive experiments show the good performance of the proposed method and its robustness against abrupt changes of illumination and shadows.
Background subtraction with multispectral video sequences
International audience; Motion analysis of moving targets is an important issue in several applications such as video surveillance or robotics. Background subtraction is one of the simplest and widely used techniques for moving target detection in video sequences. In this paper, we investigate the advantages of using a multispectral video acquisition system of more than three bands for background subtraction over the use of trichromatic or monochromatic video sequences. To this end, we have established a dataset of multispectral videos with a manual annotation of moving objects. To the best of our knowledge, this is the first publicly available dataset of multispectral video sequences. Expe…
A Shape-based Statistical Method to Retrieve 2D TRUS-MR Slice Correspondence for Prostate Biopsy
International audience; This paper presents a method based on shape-context and statistical measures to match interventional 2D Trans Rectal Ultrasound (TRUS) slice during prostate biopsy to a 2D Magnetic Resonance (MR) slice of a pre-acquired prostate volume. Accurate biopsy tissue sampling requires translation of the MR slice information on the TRUS guided biopsy slice. However, this translation or fusion requires the knowledge of the spatial position of the TRUS slice and this is only possible with the use of an electro-magnetic (EM) tracker attached to the TRUS probe. Since, the use of EM tracker is not common in clinical practice and 3D TRUS is not used during biopsy, we propose to per…
A spline-based non-linear diffeomorphism for multimodal prostate registration.
This paper presents a novel method for non-rigid registration of transrectal ultrasound and magnetic resonance prostate images based on a non-linear regularized framework of point correspondences obtained from a statistical measure of shape-contexts. The segmented prostate shapes are represented by shape-contexts and the Bhattacharyya distance between the shape representations is used to find the point correspondences between the 2D fixed and moving images. The registration method involves parametric estimation of the non-linear diffeomorphism between the multimodal images and has its basis in solving a set of non-linear equations of thin-plate splines. The solution is obtained as the least…
Exudate Segmentation on Retinal Atlas Space
International audience; Diabetic macular edema is characterized by hard exudates. Presence of such exudates cause vision loss in the affected areas. We present a novel approach of segmenting exudates for screening and follow-ups by building an ethnicity based statistical atlas. The chromatic distribution in such an atlas gives a good measure of probability of the pixels belonging to the healthy retinal pigments or to the abnormalities (like lesions, imaging artifacts etc.) in the retinal fundus image. Post-processing schemes are introduced in this paper for the enhancement of the edges of such exudates for final segmentation and to separate lesion from false positives. A sensitivity(recall)…
Multiscale Attention-Based Prototypical Network For Few-Shot Semantic Segmentation
International audience; Deep learning-based image understanding techniques require a large number of labeled images for training. Few-shot semantic segmentation, on the contrary, aims at generalizing the segmentation ability of the model to new categories given only a few labeled samples. To tackle this problem, we propose a novel prototypical network (MAPnet) with multiscale feature attention. To fully exploit the representative features of target classes, we firstly extract rich contextual information of labeled support images via a multiscale feature enhancement module. The learned prototypes from support features provide further semantic guidance on the query image. Then we adaptively i…
Visual tracking with omnidirectional cameras: an efficient approach
International audience; An effective technique for applying visual tracking algorithms to omni- directional image sequences is presented. The method is based on a spherical image representation which allows taking into account the distortions and nonlinear resolution of omnidirectional images. Experimental results show that both deterministic and probabilistic tracking methods can effectively be adapted in order to robustly track an object with an omnidirectional camera.
Spectral Clustering of Shape and Probability Prior Models for Automatic Prostate Segmentation in Ultrasound Images
International audience; Imaging artifacts in Transrectal Ultrasound (TRUS) images and inter-patient variations in prostate shape and size challenge computer-aided automatic or semi-automatic segmentation of the prostate. In this paper, we propose to use multiple mean parametric models derived from principal component analysis (PCA) of shape and posterior probability information to segment the prostate. In contrast to traditional statistical models of shape and intensity priors, we use posterior probability of the prostate region determined from random forest classification to build, initialize and propagate our model. Multiple mean models derived from spectral clustering of combined shape a…
A Supervised Learning Framework for Automatic Prostate Segmentation in Trans Rectal Ultrasound Images
International audience; Heterogeneous intensity distribution inside the prostate gland, significant variations in prostate shape, size, inter dataset contrast variations, and imaging artifacts like shadow regions and speckle in Trans Rectal Ultrasound (TRUS) images challenge computer aided automatic or semi-automatic segmentation of the prostate. In this paper, we propose a supervised learning schema based on random forest for automatic initialization and propagation of statistical shape and appearance model. Parametric representation of the statistical model of shape and appearance is derived from principal component analysis (PCA) of the probability distribution inside the prostate and PC…
A Coupled Schema of Probabilistic Atlas and Statistical Shape and Appearance Model for 3D Prostate Segmentation in MR Images
International audience; A hybrid framework of probabilistic atlas and statistical shape and appearance model (SSAM) is proposed to achieve 3D prostate segmentation. An initial 3D segmentation of the prostate is obtained by registering the probabilistic atlas to the test dataset with deformable Demons registration. The initial results obtained are used to initialize multiple SSAMs corresponding to the apex, central and base regions of the prostate gland to incorporate local variabilities. Multiple mean parametric models of shape and appearance are derived from principal component analysis of prior shape and intensity information of the prostate from the training data. The parameters are then…
From Nowhere to Everywhere
International audience; This paper presents a synthetic view of a variety of projects built upon an Erasmuss Mundus Master Course. It highlights double degree programs, European credits transfer, joint PhDs, research collaborations as well as few other related European projects going from Thematic Networks to another Erasmus Mundus Course.
Discrimination of retinal images containing bright lesions using sparse coded features and SVM
Diabetic Retinopathy (DR) is a chronic progressive disease of the retinal microvasculature which is among the major causes of vision loss in the world. The diagnosis of DR is based on the detection of retinal lesions such as microaneurysms, exudates and drusen in retinal images acquired by a fundus camera. However, bright lesions such as exudates and drusen share similar appearances while being signs of different diseases. Therefore, discriminating between different types of lesions is of interest for improving screening performances. In this paper, we propose to use sparse coding techniques for retinal images classification. In particular, we are interested in discriminating between retina…
A boosting approach for prostate cancer detection using multi-parametric MRI
International audience; Prostate cancer has been reported as the second most frequently diagnosed men cancers in the world. In the last decades, new imaging techniques based on MRI have been developed in order to improve the diagnosis task of radiologists. In practise, diagnosis can be affected by multiple factors reducing the chance to detect potential lesions. Computer-aided detection and computer-aided diagnosis have been designed to answer to these needs and provide help to radiologists in their daily duties. In this study, we proposed an automatic method to detect prostate cancer from a per voxel manner using 3T multi-parametric Magnetic Resonance Imaging (MRI) and a gradient boosting …
Ghost Detection and Removal for High Dynamic Range Images: Recent Advances
23 pages; International audience; High dynamic range (HDR) image generation and display technologies are becoming increasingly popular in various applications. A standard and commonly used approach to obtain an HDR image is the multiple exposures fusion technique which consists of combining multiple images of the same scene with varying exposure times. However, if the scene is not static during the sequence acquisition, moving objects manifest themselves as ghosting artefacts in the final HDR image. Detecting and removing ghosting artefacts is an important issue for automatically generating HDR images of dynamic scenes. The aim of this paper is to provide an up-to-date review of the recentl…
Classification of Melanoma Lesions Using Sparse Coded Features and Random Forests
International audience; Malignant melanoma is the most dangerous type of skin cancer, yet it is the most treatable kind of cancer, conditioned by its early diagnosis which is a challenging task for clinicians and dermatologists. In this regard, CAD systems based on machine learning and image processing techniques are developed to differentiate melanoma lesions from benign and dysplastic nevi using dermoscopic images. Generally, these frameworks are composed of sequential processes: pre-processing, segmentation, and classification. This architecture faces mainly two challenges: (i) each process is complex with the need to tune a set of parameters, and is specific to a given dataset; (ii) the…
Localisation Basée Vision : de l'hétérogénéité des approches et des données
National audience; De nos jours, nous disposons d'une grande diversité de données sur les lieux qui nous entourent. Ces données peuvent être de natures très différentes : une collection d'images, un modèle 3D, un nuage de points colorisés, etc. Lorsque les GPS font défaut, ces informations peuvent être très utiles pour localiser un agent dans son environnement s'il peut lui-même acquérir des informations à partir d'un système de vision. On parle alors de Localisation Basée Vision (LBV). De par la grande hétérogénéité des données acquises et connues sur l'environnement, il existe de nombreux travaux traitant de ce problème. Cet article a pour objet de passer en revue les différentes méthodes…
Statistical atlas based exudate segmentation
International audience; Diabetic macular edema (DME) is characterized by hard exudates. In this article, we propose a novel statistical atlas based method for segmentation of such exudates. Any test fundus image is first warped on the atlas co-ordinate and then a distance map is obtained with the mean atlas image. This leaves behind the candidate lesions. Post-processing schemes are introduced for final segmentation of the exudate. Experiments with the publicly available HEI-MED data-set shows good performance of the method. A lesion localization fraction of 82.5% at 35% of non-lesion localization fraction on the FROC curve is obtained. The method is also compared to few most recent referen…
Une approche performante de suivi visuel pour les caméras catadioptriques
Session "Posters"; National audience; Dans cet article, nous proposons une méthode performante permettant d'appliquer des algorithmes de suivi visuel à des images catadioptriques. Cette méthode est basée sur une représentation sphérique de l'image qui permet de prendre en compte les distorsions et la résolution non-uniforme des images catadioptriques. Les résultats expérimentaux proposés démontrent que les méthodes probabilistes et déterministes peuvent être adaptées de manière à suivre un objet avec précision dans une séquence d'images catadioptriques
Contributions à l'analyse et à l'interprétation des images : Extraction et représentation de caractéristiques
Ce mémoire, rédigé en vue de l'obtention de l'Habilitation à Diriger des Recherches (HDR), offre un aperçu des travaux de recherche et d’encadrement que j’ai pu mener depuis l'obtention de mon doctorat. Il montre la diversité des champs d’application et de recherche (en vision et en imagerie médicale) que j’ai pu couvrir , ainsi que mon implication dans l’encadrement doctoral.Mes activités de recherche se divisent en deux grandes parties. D'une part, l'analyse de scènes dynamiques, à savoir la détection de regions d'intérêt dans des séquences d'images, pour réduire la taile des données à traiter, et la détection et le suivi d'objets mobiles à l'aide de caméras de diverses natures (perspecti…
Automatic spatial and temporal organization of long range video sequences from low level motion features
International audience; In this paper, we address the analysis of activities from long range video sequences. We present a method to automatically extract spatial and temporal structure from a video sequence from low level motion features. The scene layout is first extracted, with a set of regions that have homogeneous activities called Motion Patterns. These regions are then analyzed and the recurrent temporal motifs are extracted for each Motion Patterns. Preliminary results show that our method can accurately extract important temporal motifs from video surveillance sequences.
Classification of SD-OCT volumes with multi pyramids, LBP and HOG descriptors: application to DME detections.
This paper deals with the automated detection of Diabetic Macular Edema (DME) on Optical Coherence Tomography (OCT) volumes. Our method considers a generic classification pipeline with preprocessing for noise removal and flattening of each B-Scan. Features such as Histogram of Oriented Gradients (HOG) and Local Binary Patterns (LBP) are extracted and combined to create a set of different feature vectors which are fed to a linear-Support Vector Machines (SVM) Classifier. Experimental results show a promising sensitivity/specificity of 0.75/0.87 on a challenging dataset.
Statistical atlas based exudate segmentation
Diabetic macular edema (DME) is characterized by hard exudates. In this article, we propose a novel statistical atlas based method for segmentation of such exudates. Any test fundus image is first warped on the atlas co-ordinate and then a distance map is obtained with the mean atlas image. This leaves behind the candidate lesions. Post-processing schemes are introduced for final segmentation of the exudate. Experiments with the publicly available HEI-MED data-set shows good performance of the method. A lesion localization fraction of 82.5% at 35% of non-lesion localization fraction on the FROC curve is obtained. The method is also compared to few most recent reference methods.
Polarimetric image augmentation
Robotics applications in urban environments are subject to obstacles that exhibit specular reflections hampering autonomous navigation. On the other hand, these reflections are highly polarized and this extra information can successfully be used to segment the specular areas. In nature, polarized light is obtained by reflection or scattering. Deep Convolutional Neural Networks (DCNNs) have shown excellent segmentation results, but require a significant amount of data to achieve best performances. The lack of data is usually overcomed by using augmentation methods. However, unlike RGB images, polarization images are not only scalar (intensity) images and standard augmentation techniques cann…
Structure from motion using a hybrid stereo-vision system
International audience; This paper is dedicated to robotic navigation using an original hybrid-vision setup combining the advantages offered by two different types of camera. This couple of cameras is composed of one perspective camera associated with one fisheye camera. This kind of configuration , is also known under the name of foveated vision system since it is inspired by the human vision system and allows both a wide field of view and a detail front view of the scene. Here, we propose a generic and robust approach for SFM, which is compatible with a very broad spectrum of multi-camera vision systems, suitable for perspective and om-nidirectional cameras, with or without overlapping fi…
P2D: a self-supervised method for depth estimation from polarimetry
Monocular depth estimation is a recurring subject in the field of computer vision. Its ability to describe scenes via a depth map while reducing the constraints related to the formulation of perspective geometry tends to favor its use. However, despite the constant improvement of algorithms, most methods exploit only colorimetric information. Consequently, robustness to events to which the modality is not sensitive to, like specularity or transparency, is neglected. In response to this phenomenon, we propose using polarimetry as an input for a self-supervised monodepth network. Therefore, we propose exploiting polarization cues to encourage accurate reconstruction of scenes. Furthermore, we…
Myocardial Infarction Quantification from Late Gadolinium Enhancement MRI Using Top-Hat Transforms and Neural Networks
Significance: Late gadolinium enhanced magnetic resonance imaging (LGE-MRI) is the gold standard technique for myocardial viability assessment. Although the technique accurately reflects the damaged tissue, there is no clinical standard for quantifying myocardial infarction (MI), demanding most algorithms to be expert dependent. Objectives and Methods: In this work a new automatic method for MI quantification from LGE-MRI is proposed. Our novel segmentation approach is devised for accurately detecting not only hyper-enhanced lesions, but also microvascular-obstructed areas. Moreover, it includes a myocardial disease detection step which extends the algorithm for working under healthy scans.…
Classifying DME vs Normal SD-OCT volumes: A review
International audience; This article reviews the current state of automatic classification methodologies to identify Diabetic Macular Edema (DME) versus normal subjects based on Spectral Domain OCT (SD-OCT) data. Addressing this classification problem has valuable interest since early detection and treatment of DME play a major role to prevent eye adverse effects such as blindness. The main contribution of this article is to cover the lack of a public dataset and benchmark suited for classifying DME and normal SD-OCT volumes, providing our own implementation of the most relevant methodologies in the literature. Subsequently, 6 different methods were implemented and evaluated using this comm…
Joint Probability of Shape and Image Similarities to Retrieve 2D TRUS-MR Slice Correspondence for Prostate Biopsy
International audience; This paper presents a novel method to identify the 2D axial Magnetic Resonance (MR) slice from a pre-acquired MR prostate volume that closely corresponds to the 2D axial Transrectal Ultrasound (TRUS) slice obtained during prostate biopsy. The method combines both shape and image intensity information. The segmented prostate contours in both the imaging modalities are described by shape-context representations and matched using the Chi-square distance. Normalized mutual information and correlation coefficient between the TRUS and MR slices are computed to find image similarities. Finally, the joint probability values comprising shape and image similarities are used in…
Spatio-Temporal Saliency Detection in Dynamic Scenes using Local Binary Patterns
International audience; Visual saliency detection is an important step in many computer vision applications, since it reduces further processing steps to regions of interest. Saliency detection in still images is a well-studied topic. However, videos scenes contain more information than static images, and this additional temporal information is an important aspect of human perception. Therefore, it is necessary to include motion information in order to obtain spatio-temporal saliency map for a dynamic scene. In this paper, we introduce a new spatio-temporal saliency detection method for dynamic scenes based on dynamic textures computed with local binary patterns. In particular, we extract l…
Perspective-n-Learned-Point: Pose Estimation from Relative Depth
International audience; In this paper we present an online camera pose estimation method that combines Content-Based Image Retrieval (CBIR) and pose refinement based on a learned representation of the scene geometry extracted from monocular images. Our pose estimation method is two-step, we first retrieve an initial 6 Degrees of Freedom (DoF) location of an unknown-pose query by retrieving the most similar candidate in a pool of geo-referenced images. In a second time, we refine the query pose with a Perspective-n-Point (PnP) algorithm where the 3D points are obtained thanks to a generated depth map from the retrieved image candidate. We make our method fast and lightweight by using a commo…
Détection robuste de mouvement par histogrammes quasi‐continus
National audience; Dans cet article, nous proposons d'utiliser la représentation de distributions de valeurs par histogrammes quasi-continus pour réaliser une détection temps réel de mouvement dans une séquence d'images. Nous comparons les résultats de cette détection à deux méthodes de référence de la littérature.
Steerable wavelet transform for atlas based retinal lesion segmentation
International audience; Computer aided diagnosis and follow up can help in prevention and treatment of diabetes and its related complications. Screening of diabetes related disease in the eyes is done by a special low cost fundus camera. A follow up of the patients visiting at di fferent time intervals for screening brings us to the problem of image analysis for change detection and its cost per patient. It is very likely that human annotations for the lesions may be erroneous and often time consuming. Since the ethnic background plays a signi cant role in retinal pigment epithelium, visibility of the choroidal vasculature and overall retinal luminance in patients and retinal images, an eth…
Road Signs Detection and Reconstruction using Gielis Curves
International audience; Road signs are among the most important navigation tools in transportation systems. The identification of road signs in images is usually based on first detecting road signs location using color and shape information. In this paper, we introduce such a two-stage detection method. Road signs are located in images based on color segmentation, and their corresponding shape is retrieved using a unified shape representation based on Gielis curves. The contribution of our approach is the shape reconstruction method which permits to detect any common road sign shape, i.e. circle, triangle, rectangle and octagon, by a single algorithm without any training phase. Experimental…
Automated Detection of Microaneurysms Using Scale-Adapted Blob Analysis and Semi-Supervised Learning
International audience; Despite several attempts, automated detection of microaneurysm (MA) from digital fundus images still remains to be an open issue. This is due to the subtle nature of MAs against the surrounding tissues. In this paper, the microaneurysm detection problem is modeled as finding interest regions or blobs from an image and an automatic local-scale selection technique is presented. Several scale-adapted region descriptors are then introduced to characterize these blob regions. A semi-supervised based learning approach, which requires few manually annotated learning examples, is also proposed to train a classifier to detect true MAs. The developed system is built using only…
Noise Robustness Analysis of Point Cloud Descriptors
In this paper, we investigate the effect of noise on 3D point cloud descriptors. Various types of point cloud descriptors have been introduced in the recent years due to advances in computing power, which makes processing point cloud data more feasible. Most of these descriptors describe the orientation difference between pairs of 3D points in the object and represent these differences in a histogram. Earlier studies dealt with the performances of different point cloud descriptors; however, no study has ever discussed the effect of noise on the descriptors performances. This paper presents a comparison of performance for nine different local and global descriptors amidst 10 varying levels o…
Automated detection of microaneurysms using robust blob descriptors
International audience; Microaneurysms (MAs) are among the first signs of diabetic retinopathy (DR) that can be seen as round dark-red structures in digital color fundus photographs of retina. In recent years, automated computer-aided detection and diagnosis (CAD) of MAs has attracted many researchers due to its low-cost and versatile nature. In this paper, the MA detection problem is modeled as finding interest points from a given image and several interest point descriptors are introduced and integrated with machine learning techniques to detect MAs. The proposed approach starts by applying a novel fundus image contrast enhancement technique using Singular Value Decomposition (SVD) of fun…
Classification of SD-OCT Volumes with LBP: Application to DME Detection
International audience; This paper addresses the problem of automatic classification of Spectral Domain OCT (SD-OCT) data for automatic identification of patients with Diabetic Macular Edema (DME) versus normal subjects. Our method is based on Local Binary Patterns (LBP) features to describe the texture of Optical Coherence Tomography (OCT) images and we compare different LBP features extraction approaches to compute a single signature for the whole OCT volume. Experimental results with two datasets of respectively 32 and 30 OCT volumes show that regardless of using low or high level representations, features derived from LBP texture have highly discriminative power. Moreover, the experimen…
Bag of words representation and SVM classifier for timber knots detection on color images
Knots as well as their density have a huge impact on the mechanical properties of wood boards. This paper addresses the issue of their automatic detection. An image processing pipeline which associates low level processing (contrast enhancement, thresholding, mathematical morphology) with bag-of-words approach is developed. We propose a SVM classification based on features obtained by SURF descriptors on RGB images, followed by a dictionary created using the bag-of-words approach. Our method was tested on color images from two different datasets with a total number of 640 knots. The mean recall (true positive) rate achieved was (92%) and (97%) for a single dictionary (built only on samples …