0000000000451072
AUTHOR
Désiré Sidibé
Computer Aided Design for Diabetic Retinopathy
International audience; Computer aided diagnosis and follow up can help in prevention and treatment of diabetes and its related complications. This paper presents a summary of the results we obtained over the last few years regarding the development of a CAD system for diabetic retinopathy. We present a methodology for diagnosis of DME based on exudates segmentation, as well as an automated detection of micro-aneurysm (MA) and DR diagnosis; Our approach uses standard available public database and shows a high power of generalization through cross database experiments.
Supervised Learning Framework of Statistical Shape and Probability Priors for Automatic Prostate Segmentation in Ultrasound Images
International audience
A Note about Eigenvalues, SVD and PCA
Notes on eigen-decomposition, PCA, SVD and connexions.
Hand Gestures Recognition and Tracking
In this project we develop a system that uses low cost web cameras to recognise gestures and track 2D orientations of the hand. This report is organized as such. First in section 2 we introduce various methods we undertook for hand detection. This is the most important step in hand gesture recognition. Results of various skin detection algorithms are discussed in length. This is followed by region extraction step (section 3). In this section approaches like contours and convex hull to extract region of interest which is hand are discussed. In section 4 a method is describe to recognize the open hand gesture. Two additional gestures of palm and fist are implemented using Haar-like features. …
Using Visual Saliency for Object Tracking with Particle Filters
International audience; This paper presents a robust tracking method based on the integration of visual saliency information into the particle filter framework. While particle filter has been successfully used for tracking non-rigid objects, it shows poor performances in the presence of large illumination variation, occlusions and when the target object and background have similar color distributions. We show that considering saliency information significantly improves the performance of particle filter based tracking. In particular, the proposed method is robust against occlusion and large illumination variation while requiring a reduced number of particles. Experimental results demonstrate th…
Self-Calibration of PTZ Camera using New LMI Constraints
International audience
On Keyframe Positioning for Pose Graphs Applied to Visual SLAM
International audience; In this work, a new method is introduced for localization and keyframe identification to solve a Simultaneous Localization and Mapping (SLAM) problem. The proposed approach is based on a dense spherical acquisition system that synthesizes spherical intensity and depth images at arbitrary locations. The images are related by a graph of 6 degrees-of-freedom (DOF) poses which are estimated through spherical registration. A direct image-based method is provided to estimate pose by using both depth and color information simultaneously. A new keyframe identification method is proposed to build the map of the environment by using the covariance matrix between raletive 6 DOF…
Control of a PTZ camera in a hybrid vision system
In this paper, we propose a new approach to steer a PTZ camera in the direction of a detected object visible from another fixed camera equipped with a fisheye lens. This heterogeneous association of two cameras having different characteristics is called a hybrid stereo-vision system. The presented method employs epipolar geometry in a smart way in order to reduce the range of search of the desired region of interest. Furthermore, we proposed a target recognition method designed to cope with the illumination problems, the distortion of the omnidirectional image and the inherent dissimilarity of resolution and color responses between both cameras. Experimental results with synthetic and real …