This thesis deals with the synthesis of anisotropic volumetric textures from a single 2D observation. We present variants of non parametric and multi-scale algorithms. Their main specificity lies in the fact that the 3D synthesis process relies on the sampling of a single 2D input sample, ensuring consistency in the different views of the 3D texture. Two types of approaches are investigated, both multi-scale and based on markovian hypothesis. The first category brings together a set of algorithms based on fixed-neighbourhood search, adapted from existing algorithms of texture synthesis from multiple 2D sources. The principle is that, starting from a random initialisation, the 3D texture is modified, voxel by voxel, in a deterministic manner, ensuring that the grey level local configurations on orthogonal slices containing the voxel are similar to configurations of the input image. The second category points out an original probabilistic approach which aims at reproducing in the textured volume the interactions between pixels learned in the input image. The learning is done by non-parametric Parzen windowing. Optimization is handled voxel by voxel by a deterministic ICM type algorithm. Several variants are proposed regarding the strategies used for the simultaneous handling of the orthogonal slices containing the voxel. These synthesis methods are first implemented on a set of structured textures of varied regularity and anisotropy. A comparative study and a sensitivity analysis are carried out, highlighting the strengths and the weaknesses of the different algorithms. Finally, they are applied to the simulation of volumetric textures of carbon composite materials, on nanometric scale snapshots obtained by transmission electron microscopy. The proposed experimental benchmark allows to evaluate quantitatively and objectively the performances of the different methods.

This Ph.D. thesis tackles the issue of sill and video object categorization. The objective is to associate semantic labels to 2D objects present in natural images/videos. The principle of the proposed approach consists of exploiting categorized 3D model repositories in order to identify unknown 2D objects based on 2D/3D matching techniques. We propose here an object recognition framework, designed to work for real time applications. The similarity between classified 3D models and unknown 2D content is evaluated with the help of the 2D/3D description. A voting procedure is further employed in order to determine the most probable categories of the 2D object. A representative viewing angle selection strategy and a new contour based descriptor (so-called AH), are proposed. The experimental evaluation proved that, by employing the intelligent selection of views, the number of projections can be decreased significantly (up to 5 times) while obtaining similar performance. The results have also shown the superiority of AH with respect to other state of the art descriptors. An objective evaluation of the intra and inter class variability of the 3D model repositories involved in this work is also proposed, together with a comparative study of the retained indexing approaches . An interactive, scribble-based segmentation approach is also introduced. The proposed method is specifically designed to overcome compression artefacts such as those introduced by JPEG compression. We finally present an indexing/retrieval/classification Web platform, so-called Diana, which integrates the various methodologies employed in this thesis

Cette thèse porte sur la catégorisation d'objets vidéo. L'objectif est d'associer des étiquettes sémantiques à des objets 2D présents dans les images/vidéos. L'approche proposée consiste à exploiter des bases d'objets 3D classifiés afin d'identifier des objets 2D inconnus. Nous proposons un schéma de reconnaissance d'objet, conçu pour fonctionner pour des applications en temps réel. La similitude entre des modèles 3D et des contenus 2D inconnu est évaluée à l'aide de la description 2D/3D. Une procédure de vote est ensuite utilisée afin de déterminer les catégories les plus probables de l'objet 2D. Nous proposons aussi une stratégie pour la sélection des vues les plus représentatives d'un objet 3D et un nouveau descripteur de contour (nommé AH). L'évaluation expérimentale a montré que, en employant la sélection intelligente de vues, le nombre de projections peut être diminué de manière significative (jusqu'à 5 fois) tout en obtenant des performances similaires. Les résultats ont également montré la supériorité de l'AH par rapport aux autres descripteurs adoptés. Une évaluation objective de la variabilité intra et inter classe des bases de données 3D impliqués dans ce travail est également proposé, ainsi qu'une étude comparative des approches d'indexations retenues. Une approche de segmentation interactive est également introduite. La méthode proposée est spécifiquement conçu pour surmonter les artefacts de compression tels que ceux mis en place par la compression JPEG. Enfin, nous présentons une plate-forme Web pour l'indexation/la recherche/la classification, qui intègre les différentes méthodologies utilisées dans cette thèse / This Ph.D. thesis tackles the issue of sill and video object categorization. The objective is to associate semantic labels to 2D objects present in natural images/videos. The principle of the proposed approach consists of exploiting categorized 3D model repositories in order to identify unknown 2D objects based on 2D/3D matching techniques. We propose here an object recognition framework, designed to work for real time applications. The similarity between classified 3D models and unknown 2D content is evaluated with the help of the 2D/3D description. A voting procedure is further employed in order to determine the most probable categories of the 2D object. A representative viewing angle selection strategy and a new contour based descriptor (so-called AH), are proposed. The experimental evaluation proved that, by employing the intelligent selection of views, the number of projections can be decreased significantly (up to 5 times) while obtaining similar performance. The results have also shown the superiority of AH with respect to other state of the art descriptors. An objective evaluation of the intra and inter class variability of the 3D model repositories involved in this work is also proposed, together with a comparative study of the retained indexing approaches . An interactive, scribble-based segmentation approach is also introduced. The proposed method is specifically designed to overcome compression artefacts such as those introduced by JPEG compression. We finally present an indexing/retrieval/classification Web platform, so-called Diana, which integrates the various methodologies employed in this thesis

Ce mémoire traite de synthèse de textures volumiques anisotropes à partir d’une observation 2D unique. Nous présentons différentes variantes d’algorithmes non paramétriques et multi-échelles. Leur principale particularité réside dans le fait que le processus de synthèse 3D s’appuie sur l’échantillonnage d’une seule image 2D d’entrée, en garantissant la cohérence selon les différentes vues de la texture 3D. Deux catégories d’approches sont abordées, toutes deux multi-échelles et basées sur une hypothèse markovienne. La première catégorie regroupe un ensemble d’algorithmes dits de recherche de voisinages fixes, adaptés d’algorithmes existants de synthèses de textures volumiques à partir de sources 2D multiples. Le principe consiste, à partir d’une initialisation aléatoire, à modifier les voxels un par un, de façon déterministe, en s’assurant que les configurations locales de niveaux de gris sur des tranches orthogonales contenant le voxel sont semblables à des configurations présentes sur l’image d’entrée. La deuxième catégorie relève d’une approche probabiliste originale dont l’objectif est de reproduire, sur le volume texturé, les interactions entre pixels estimées sur l’image d’entrée. L’estimation est réalisée de façon non paramétrique par fenêtrage de Parzen. L’optimisation est gérée voxel par voxel, par un algorithme déterministe de type ICM. Différentes variantes sont proposées, relatives aux stratégies de gestion simultanée des tranches orthogonales contenant le voxel. Ces différentes méthodes sont d’abord mises en œuvre pour la synthèse d’un jeu de textures structurées, de régularité et d’anisotropie variées. Une analyse comparée et une étude de sensibilité sont menées, mettant en évidence les atouts et faiblesses des différentes approches. Enfin, elles sont appliquées à la simulation de textures volumiques de matériaux composites carbonés, à partir de clichés obtenus à l’échelle nanométrique par microscopie électronique à transmission. Le schéma expérimental proposé permet d’évaluer quantitativement et de façon objective les performances des différentes méthodes. / This thesis deals with the synthesis of anisotropic volumetric textures from a single 2D observation. We present variants of non parametric and multi-scale algorithms. Their main specificity lies in the fact that the 3D synthesis process relies on the sampling of a single 2D input sample, ensuring consistency in the different views of the 3D texture. Two types of approaches are investigated, both multi-scale and based on markovian hypothesis. The first category brings together a set of algorithms based on fixed-neighbourhood search, adapted from existing algorithms of texture synthesis from multiple 2D sources. The principle is that, starting from a random initialisation, the 3D texture is modified, voxel by voxel, in a deterministic manner, ensuring that the grey level local configurations on orthogonal slices containing the voxel are similar to configurations of the input image. The second category points out an original probabilistic approach which aims at reproducing in the textured volume the interactions between pixels learned in the input image. The learning is done by non-parametric Parzen windowing. Optimization is handled voxel by voxel by a deterministic ICM type algorithm. Several variants are proposed regarding the strategies used for the simultaneous handling of the orthogonal slices containing the voxel. These synthesis methods are first implemented on a set of structured textures of varied regularity and anisotropy. A comparative study and a sensitivity analysis are carried out, highlighting the strengths and the weaknesses of the different algorithms. Finally, they are applied to the simulation of volumetric textures of carbon composite materials, on nanometric scale snapshots obtained by transmission electron microscopy. The proposed experimental benchmark allows to evaluate quantitatively and objectively the performances of the different methods.