Made available in DSpace on 2014-06-11T19:26:56Z (GMT). No. of bitstreams: 0 Previous issue date: 2010-02-25Bitstream added on 2014-06-13T19:06:36Z : No. of bitstreams: 1 casaca_wco_me_sjrp.pdf: 5215634 bytes, checksum: 291e2a21fdb4d46a11de22f18cc97f93 (MD5) / Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP) / Neste trabalho propomos quatro novas abordagens para tratar o problema de restauração de imagens reais contendo texturas sob a perspectiva dos temas: reconstrução de regiões danificadas, remoção de objetos, e eliminação de ruídos. As duas primeiras abor dagens são designadas para recompor partes perdias ou remover objetos de uma imagem real a partir de formulações envolvendo decomposiçãode imagens e inpainting por exem- plar, enquanto que as duas últimas são empregadas para remover ruído, cujas formulações são baseadas em decomposição de três termos e equações diferenciais parciais não lineares. Resultados experimentais atestam a boa performace dos protótipos apresentados quando comparados à modelagens correlatas da literatura. / In this paper we propose four new approaches to address the problem of restoration of real images containing textures from the perspective of reconstruction of damaged areas, object removal, and denoising topics. The first two approaches are designed to reconstruct missing parts or to remove objects of a real image using formulations based on image de composition and exemplar based inpainting, while the last two other approaches are used to remove noise, whose formulations are based on decomposition of three terms and non- linear partial di®erential equations. Experimental results attest to the good performance of the presented prototypes when compared to modeling related in literature.

Orientador: Maurílio Boaventura / Banca: Evanildo Castro Silva Júnior / Banca: Alagacone Sri Ranga / Resumo: Neste trabalho propomos quatro novas abordagens para tratar o problema de restauração de imagens reais contendo texturas sob a perspectiva dos temas: reconstrução de regiões danificadas, remoção de objetos, e eliminação de ruídos. As duas primeiras abor dagens são designadas para recompor partes perdias ou remover objetos de uma imagem real a partir de formulações envolvendo decomposiçãode imagens e inpainting por exem- plar, enquanto que as duas últimas são empregadas para remover ruído, cujas formulações são baseadas em decomposição de três termos e equações diferenciais parciais não lineares. Resultados experimentais atestam a boa performace dos protótipos apresentados quando comparados à modelagens correlatas da literatura. / Abstract: In this paper we propose four new approaches to address the problem of restoration of real images containing textures from the perspective of reconstruction of damaged areas, object removal, and denoising topics. The first two approaches are designed to reconstruct missing parts or to remove objects of a real image using formulations based on image de composition and exemplar based inpainting, while the last two other approaches are used to remove noise, whose formulations are based on decomposition of three terms and non- linear partial di®erential equations. Experimental results attest to the good performance of the presented prototypes when compared to modeling related in literature. / Mestre

Dans cette thèse, on étudie la structuration des phases de la transformée de Fourier d'images naturelles, ce qui, du point de vue applicatif, débouche sur plusieurs mesures de netteté ainsi que sur des algorithmes rapides pour la synthèse de texture par l'exemple. Le Chapitre 2 présente dans un cadre unifié plusieurs modèles de champs aléatoires, notamment les champs spot noise et champs gaussiens, en prêtant une attention particulière aux représentations fréquentielles de ces champs aléatoires. Le Chapitre 3 détaille l'utilisation des champs à phase aléatoire à la synthèse de textures peu structurées (microtextures). On montre qu'une microtexture peut être résumée en une image de petite taille s'intégrant à un algorithme de synthèse très rapide et flexible via le modèle spot noise. Aussi on propose un algorithme de désocclusion de zones texturales uniformes basé sur la simulation gaussienne conditionnelle. Le Chapitre 4 présente trois mesures de cohérence globale des phases de la transformée de Fourier. Après une étude théorique et pratique établissant leur lien avec la netteté d'image, on propose un algorithme de déflouage aveugle basé sur l'optimisation stochastique de ces indices. Enfin, dans le Chapitre 5, après une discussion sur l'analyse et la synthèse directe de l'information de phase, on propose deux modèles de textures à phases cohérentes qui permettent la synthèse de textures plus structurées tout en conservant quelques garanties mathématiques simples. / This thesis deals with the Fourier phase structure of natural images, and addresses no-reference sharpness assessment and fast texture synthesis by example. In Chapter 2, we present several models of random fields in a unified framework, like the spot noise model and the Gaussian model, with particular attention to the spectral representation of these random fields. In Chapter 3, random phase models are used to perform by-example synthesis of microtextures (textures with no salient features). We show that a microtexture can be summarized by a small image that can be used for fast and flexible synthesis based on the spot noise model. Besides, we address microtexture inpainting through the use of Gaussian conditional simulation. In Chapter 4, we present three measures of the global Fourier phase coherence. Their link with the image sharpness is established based on a theoretical and practical study. We then derive a stochastic optimization scheme for these indices, which leads to a blind deblurring algorithm. Finally, in Chapter 5, after discussing the possibility of direct phase analysis or synthesis, we propose two non random phase texture models which allow for synthesis of more structured textures and still have simple mathematical guarantees.

Le but de cette thèse est de proposer une modélisation mathématique des stimulations visuelles afin d'analyser finement des données expérimentales en psychophysique et en électrophysiologie. Plus précis\'ement, afin de pouvoir exploiter des techniques d'analyse de données issues des statistiques Bayésiennes et de l'apprentissage automatique, il est nécessaire de développer un ensemble de stimulations qui doivent être dynamiques, stochastiques et d'une complexité paramétrée. Il s'agit d'un problème important afin de comprendre la capacité du système visuel à intégrer et discriminer différents stimuli. En particulier, les mesures effectuées à de multiples échelles (neurone, population de neurones, cognition) nous permette d'étudier les sensibilités particulières des neurones, leur organisation fonctionnelle et leur impact sur la prise de décision. Dans ce but, nous proposons un ensemble de contributions théoriques, numériques et expérimentales, organisées autour de trois axes principaux : (1) un modèle de synthèse de textures dynamiques Gaussiennes spécialement paramétrée pour l'étude de la vision; (2) un modèle d'observateur Bayésien rendant compte du biais positif induit par fréquence spatiale sur la perception de la vitesse; (3) l'utilisation de méthodes d'apprentissage automatique pour l'analyse de données obtenues en imagerie optique par colorant potentiométrique et au cours d'enregistrements extra-cellulaires. Ce travail, au carrefour des neurosciences, de la psychophysique et des mathématiques, est le fruit de plusieurs collaborations interdisciplinaires. / The goal of this thesis is to propose a mathematical model of visual stimulations in order to finely analyze experimental data in psychophysics and electrophysiology. More precisely, it is necessary to develop a set of dynamic, stochastic and parametric stimulations in order to exploit data analysis techniques from Bayesian statistics and machine learning. This problem is important to understand the visual system capacity to integrate and discriminate between stimuli. In particular, the measures performed at different scales (neurons, neural population, cognition) allow to study the particular sensitivities of neurons, their functional organization and their impact on decision making. To this purpose, we propose a set of theoretical, numerical and experimental contributions organized around three principal axes: (1) a Gaussian dynamic texture synthesis model specially crafted to probe vision; (2) a Bayesian observer model that accounts for the positive effect of spatial frequency over speed perception; (3) the use of machine learning techniques to analyze voltage sensitive dye optical imaging and extracellular data. This work, at the crossroads of neurosciences, psychophysics and mathematics is the fruit of several interdisciplinary collaborations.

This thesis introduces a multilinear algebraic framework for computer graphics, computer vision, and machine learning, particularly for the fundamental purposes of image synthesis, analysis, and recognition. Natural images result from the multifactor interaction between the imaging process, the scene illumination, and the scene geometry. We assert that a principled mathematical approach to disentangling and explicitly representing these causal factors, which are essential to image formation, is through numerical multilinear algebra, the algebra of higher-order tensors. Our new image modeling framework is based on(i) a multilinear generalization of principal components analysis (PCA), (ii) a novel multilinear generalization of independent components analysis (ICA), and (iii) a multilinear projection for use in recognition that maps images to the multiple causal factor spaces associated with their formation. Multilinear PCA employs a tensor extension of the conventional matrix singular value decomposition (SVD), known as the M-mode SVD, while our multilinear ICA method involves an analogous M-mode ICA algorithm. As applications of our tensor framework, we tackle important problems in computer graphics, computer vision, and pattern recognition; in particular, (i) image-based rendering, specifically introducing the multilinear synthesis of images of textured surfaces under varying view and illumination conditions, a new technique that we call ``TensorTextures'', as well as (ii) the multilinear analysis and recognition of facial images under variable face shape, view, and illumination conditions, a new technique that we call ``TensorFaces''. In developing these applications, we introduce a multilinear image-based rendering algorithm and a multilinear appearance-based recognition algorithm. As a final, non-image-based application of our framework, we consider the analysis, synthesis and recognition of human motion data using multilinear methods, introducing a new technique that we call ``Human Motion Signatures''.

This thesis introduces a multilinear algebraic framework for computer graphics, computer vision, and machine learning, particularly for the fundamental purposes of image synthesis, analysis, and recognition. Natural images result from the multifactor interaction between the imaging process, the scene illumination, and the scene geometry. We assert that a principled mathematical approach to disentangling and explicitly representing these causal factors, which are essential to image formation, is through numerical multilinear algebra, the algebra of higher-order tensors. Our new image modeling framework is based on(i) a multilinear generalization of principal components analysis (PCA), (ii) a novel multilinear generalization of independent components analysis (ICA), and (iii) a multilinear projection for use in recognition that maps images to the multiple causal factor spaces associated with their formation. Multilinear PCA employs a tensor extension of the conventional matrix singular value decomposition (SVD), known as the M-mode SVD, while our multilinear ICA method involves an analogous M-mode ICA algorithm. As applications of our tensor framework, we tackle important problems in computer graphics, computer vision, and pattern recognition; in particular, (i) image-based rendering, specifically introducing the multilinear synthesis of images of textured surfaces under varying view and illumination conditions, a new technique that we call ``TensorTextures'', as well as (ii) the multilinear analysis and recognition of facial images under variable face shape, view, and illumination conditions, a new technique that we call ``TensorFaces''. In developing these applications, we introduce a multilinear image-based rendering algorithm and a multilinear appearance-based recognition algorithm. As a final, non-image-based application of our framework, we consider the analysis, synthesis and recognition of human motion data using multilinear methods, introducing a new technique that we call ``Human Motion Signatures''.