Dans cette thèse, nous traitons de la compréhension de contenus visuels, qu’il s’agisse d’images, de vidéos ou encore de contenus 3D. On entend par compréhension la capacité à inférer des informations sémantiques sur le contenu visuel. L’objectif de ce travail est d’étudier des méthodes combinant deux approches : 1) l’analyse automatique des contenus et 2) l’analyse des interactions liées à l’utilisation de ces contenus (analyse des usages, en plus bref). Dans un premier temps, nous étudions l’état de l’art issu des communautés de la vision par ordinateur et du multimédia. Il y a 20 ans, l’approche dominante visait une compréhension complètement automatique des images. Cette approche laisse aujourd’hui plus de place à différentes formes d’interventions humaines. Ces dernières peuvent se traduire par la constitution d’une base d’apprentissage annotée, par la résolution interactive de problèmes (par exemple de détection ou de segmentation) ou encore par la collecte d’informations implicites issues des usages du contenu. Il existe des liens riches et complexes entre supervision humaine d’algorithmes automatiques et adaptation des contributions humaines via la mise en œuvre d’algorithmes automatiques. Ces liens sont à l’origine de questions de recherche modernes : comment motiver des intervenants humains ? Comment concevoir des scénarii interactifs pour lesquels les interactions contribuent à comprendre le contenu manipulé ? Comment vérifier la qualité des traces collectées ? Comment agréger les données d’usage ? Comment fusionner les données d’usage avec celles, plus classiques, issues d’une analyse automatique ? Notre revue de la littérature aborde ces questions et permet de positionner les contributions de cette thèse. Celles-ci s’articulent en deux grandes parties. La première partie de nos travaux revisite la détection de régions importantes ou saillantes au travers de retours implicites d’utilisateurs qui visualisent ou acquièrent des con- tenus visuels. En 2D d’abord, plusieurs interfaces de vidéos interactives (en particulier la vidéo zoomable) sont conçues pour coordonner des analyses basées sur le contenu avec celles basées sur l’usage. On généralise ces résultats en 3D avec l’introduction d’un nouveau détecteur de régions saillantes déduit de la capture simultanée de vidéos de la même performance artistique publique (spectacles de danse, de chant etc.) par de nombreux utilisateurs. La seconde contribution de notre travail vise une compréhension sémantique d’images fixes. Nous exploitons les données récoltées à travers un jeu, Ask’nSeek, que nous avons créé. Les interactions élémentaires (comme les clics) et les données textuelles saisies par les joueurs sont, comme précédemment, rapprochées d’analyses automatiques des images. Nous montrons en particulier l’intérêt d’interactions révélatrices des relations spatiales entre différents objets détectables dans une même scène. Après la détection des objets d’intérêt dans une scène, nous abordons aussi le problème, plus ambitieux, de la segmentation. / This thesis focuses on the problem of understanding visual contents, which can be images, videos or 3D contents. Understanding means that we aim at inferring semantic information about the visual content. The goal of our work is to study methods that combine two types of approaches: 1) automatic content analysis and 2) an analysis of how humans interact with the content (in other words, usage analysis). We start by reviewing the state of the art from both Computer Vision and Multimedia communities. Twenty years ago, the main approach was aiming at a fully automatic understanding of images. This approach today gives way to different forms of human intervention, whether it is through the constitution of annotated datasets, or by solving problems interactively (e.g. detection or segmentation), or by the implicit collection of information gathered from content usages. These different types of human intervention are at the heart of modern research questions: how to motivate human contributors? How to design interactive scenarii that will generate interactions that contribute to content understanding? How to check or ensure the quality of human contributions? How to aggregate human contributions? How to fuse inputs obtained from usage analysis with traditional outputs from content analysis? Our literature review addresses these questions and allows us to position the contributions of this thesis. In our first set of contributions we revisit the detection of important (or salient) regions through implicit feedback from users that either consume or produce visual contents. In 2D, we develop several interfaces of interactive video (e.g. zoomable video) in order to coordinate content analysis and usage analysis. We also generalize these results to 3D by introducing a new detector of salient regions that builds upon simultaneous video recordings of the same public artistic performance (dance show, chant, etc.) by multiple users. The second contribution of our work aims at a semantic understanding of fixed images. With this goal in mind, we use data gathered through a game, Ask’nSeek, that we created. Elementary interactions (such as clicks) together with textual input data from players are, as before, mixed with automatic analysis of images. In particular, we show the usefulness of interactions that help revealing spatial relations between different objects in a scene. After studying the problem of detecting objects on a scene, we also adress the more ambitious problem of segmentation.

No description available.

Dopamine is an important neurotransmitter that is involved in several human functions such as reward, cognition, emotions and movement. Abnormalities of the neurotransmitter itself, or the dopamine receptors through which it exerts its actions, contribute to a wide range of psychiatric and neurological disorders such as Parkinson’s disease and schizophrenia. Thus far, despite the great interest and extensive research, the exact role of dopamine and the causalities of dopamine related disorders are not fully understood. Here we have developed multimodal imaging methods, to investigate the release of dopamine and the distribution of the dopamine D2-like receptor family in-vivo in healthy humans. We use the [¹¹C]PHNO PET ligand, which enables exploration of dopamine-related parameters in striatal regions, and for the first time in extrastriatal regions, that are known to be associated with distinctive functions and disorders. Our methods involve robust approaches for the manual and automated delineation of these brain regions, in terms of structural and functional organisation, using information from structural and diffusion MRI images. These data have been combined with [¹¹C]PHNO PET data for quantitative dopamine imaging. Our investigation has revealed the distribution and the relative density of the D3R and D2R sites of the dopamine D2-like receptor family, in healthy humans. In addition, we have demonstrated that the release of dopamine has a functional rather than a structural specificity and that the relative densities of the D3R and D2R sites do not drive this specificity. We have also shown that the dopamine D3R receptor is primarily distributed in regions that have a central role in reward and addiction. A finding that supports theories that assigns a primarily limbic role to the D3R.

Made available in DSpace on 2014-12-17T14:56:22Z (GMT). No. of bitstreams: 1 DiegoMG.pdf: 1982662 bytes, checksum: e489eb42e914d358aaeb197489ceb5e4 (MD5) Previous issue date: 2006-01-05 / There has been an increasing tendency on the use of selective image compression, since several applications make use of digital images and the loss of information in certain regions is not allowed in some cases. However, there are applications in which these images are captured and stored automatically making it impossible to the user to select the regions of interest to be compressed in a lossless manner. A possible solution for this matter would be the automatic selection of these regions, a very difficult problem to solve in general cases. Nevertheless, it is possible to use intelligent techniques to detect these regions in specific cases. This work proposes a selective color image compression method in which regions of interest, previously chosen, are compressed in a lossless manner. This method uses the wavelet transform to decorrelate the pixels of the image, competitive neural network to make a vectorial quantization, mathematical morphology, and Huffman adaptive coding. There are two options for automatic detection in addition to the manual one: a method of texture segmentation, in which the highest frequency texture is selected to be the region of interest, and a new face detection method where the region of the face will be lossless compressed. The results show that both can be successfully used with the compression method, giving the map of the region of interest as an input / A compress?o seletiva de imagens tende a ser cada vez mais utilizada, visto que diversas aplica??es fazem uso de imagens digitais que em alguns casos n?o permitem perdas de informa??es em certas regi?es. Por?m, existem aplica??es nas quais essas imagens s?o capturadas e armazenadas automaticamente, impossibilitando a um usu?rio indicar as regi?es da imagem que devem ser comprimidas sem perdas. Uma solu??o para esse problema seria a detec??o autom?tica das regi?es de interesse, um problema muito dif?cil de ser resolvido em casos gerais. Em certos casos, no entanto, pode-se utilizar t?cnicas inteligentes para detectar essas regi?es. Esta disserta??o apresenta um compressor seletivo de imagens coloridas onde as regi?es de interesse, previamente fornecidas, s?o comprimidas totalmente sem perdas. Este m?todo faz uso da transformada wavelet para descorrelacionar os pixels da imagem, de uma rede neural competitiva para realizar uma quantiza??o vetorial, da morfologia matem?tica e do c?digo adaptativo de Huffman. Al?m da op??o da sele??o manual das regi?es de interesse, existem duas op??es de detec??o autom?tica: um m?todo de segmenta??o de texturas, onde a textura com maior freq??ncia ? selecionada para ser a regi?o de interesse, e um novo m?todo de detec??o de faces onde a regi?o da face ? comprimida sem perdas. Os resultados mostram que ambos os m?todos podem ser utilizados com o algoritmo de compress?o, fornecendo a este o mapa de regi?o de interesse

This thesis concerns with processing of embedded terminals’ images and their classification. There is problematics of moire noise reduction thought filtration in frequency domain and the image normalization for further processing analyzed. Keypoints detectors and descriptors are used for image classification. Detectors FAST and Harris corner detector and descriptors SURF, BRIEF and BRISK are emphasized as well as their evaluation in terms of potential contribution to this work.