National audienceFrom now on, graph cuts are a standard in the computer vision community. However, their huge memory consumption remains a challenging problem since underlying graphs contains billions of nodes and even more edges. Except some exact methods [14, 10, 5], the heuristics in the literature can only obtain an approached solution [12, 8]. First, we present a new strategy for reducing exactly these graphs : the graph is built by adding nodes which satisfy locally a given condition and corresponds in a narrow band around the segmented object edges. The experiments presented for segmenting gray-levels and color images highlight low memory usage and show a low distance between segmentations. We also present an application of this meth...
This thesis explores the use of discriminatively trained deformable contour models (DCMs) for shape-...
- Nous montrons comment un processus de segmentation peut être utilisé localement sur des régions d'...
Cette thèse est proposée en deux parties. Une première partie se concentre sur la segmentation d’ima...
8 pagesLes graph cuts sont désormais un standard au sein de la communauté de la vision par ordinateu...
Image processing techniques are now widely spread out over a large quantity of domains: like medical...
This document from the fmr group introduces four types of methods for simplifying and/or partitionin...
Dans le contexte d'une application médicale spécifique, le traitement mini-invasif des cancers primi...
Last decades have witnessed an unprecedented expansion of medical data in various largescale and com...
La segmentation d'images consiste souvent à extraire des objets afin de les caractériser et d'interp...
In the digital world, two-dimensional (2D) and three-dimensional (3D) shapes are important for repre...
National audienceThe recognition of discrete straight segments is a significant topic in the field o...
Medical imaging is one of the most active research topics in image analysis. Analyzing and segmentin...
Mathematical morphology is one of the most powerful frameworks which provides a set of filtering and...
Cet article présente une méthode de segmentation qui génère une partition perceptuellement pertinent...
National audienceNeighborhood graphs know increasing use in many fields as in Data Science, or Multi...
This thesis explores the use of discriminatively trained deformable contour models (DCMs) for shape-...
- Nous montrons comment un processus de segmentation peut être utilisé localement sur des régions d'...
Cette thèse est proposée en deux parties. Une première partie se concentre sur la segmentation d’ima...
8 pagesLes graph cuts sont désormais un standard au sein de la communauté de la vision par ordinateu...
Image processing techniques are now widely spread out over a large quantity of domains: like medical...
This document from the fmr group introduces four types of methods for simplifying and/or partitionin...
Dans le contexte d'une application médicale spécifique, le traitement mini-invasif des cancers primi...
Last decades have witnessed an unprecedented expansion of medical data in various largescale and com...
La segmentation d'images consiste souvent à extraire des objets afin de les caractériser et d'interp...
In the digital world, two-dimensional (2D) and three-dimensional (3D) shapes are important for repre...
National audienceThe recognition of discrete straight segments is a significant topic in the field o...
Medical imaging is one of the most active research topics in image analysis. Analyzing and segmentin...
Mathematical morphology is one of the most powerful frameworks which provides a set of filtering and...
Cet article présente une méthode de segmentation qui génère une partition perceptuellement pertinent...
National audienceNeighborhood graphs know increasing use in many fields as in Data Science, or Multi...
This thesis explores the use of discriminatively trained deformable contour models (DCMs) for shape-...
- Nous montrons comment un processus de segmentation peut être utilisé localement sur des régions d'...
Cette thèse est proposée en deux parties. Une première partie se concentre sur la segmentation d’ima...