Orientador: Prof. Dr. Ricardo Suyama / Dissertação (mestrado) - Universidade Federal do ABC, Programa de Pós-Graduação em Engenharia da Informação, 2015. / No processo de digitalização de documentos impressos ou manuscritos que apresentam informação em ambos os lados da folha (frente e verso), é comum encontrar uma distorção na imagem digitalizada conhecida como Efeito Show-Through, na qual a imagem digitalizada de um dos lados do documento sofre a interferência da imagem presente no outro lado da folha. O problema de remoção dessa interferência pode ser visto como uma instância do problema geral de Separação Cega de Fontes (BSS ¿ Blind Source Separation), para o qual diferentes técnicas foram propostas, baseadas nas características das fontes e no processo de mistura. No presente trabalho avaliamos diferentes técnicas para a solução do problema de Show-through que utilizam os conceitos relacionados ao problema de Separação Cega de Fontes, buscando identificar vantagens e desvantagens dos diferentes métodos. As técnicas avaliadas, baseadas em três diferentes abordagens em termos do critério de adaptação dos parâmetros, foram testadas com diferentes tipos de documentos (textos antigos ,manuscritos,jornal,etc) digitalizados, considerando misturas sintéticas e misturas reais, obtidas com a digitalização de documentos impressos. Os resultados obtidos revelam pontos fortes e fracos das técnicas avaliadas, e poderão servir como referência para o desenvolvimento de novas técnicas para a correção do efeito Show-Through. / In the digitalization process of printed documents or manuscripts that contain information on both through sides of the paper (front and back), it is common to observe the so-called Show-Thorugh Effet, in which the image in the back of the document interferes in the digitized image of the front side. Removing this kind of interference can be seen as an instance of the general Blind Source Separation Problem (BSS), for which several different techniques have been proposed in the literature, considering specific characteristics of the sources and of the mixing process. The objective of the present work is to evaluate different methods for the mitigation of the Show-Through effect, based in concepts related to the BSS problem. The evaluated tools, based on three different approaches for parameter adaptation, were tested with different kinds of documents (old texts, manuscripts, newspaper), considering synthetic and real mixtures. The results reveal strong and weak points of the studied methods, which can serve as a valuable reference in the development of new techniques for the Show-Through effect mitigation.

Cette thèse concerne la restauration aveugle d’images (formulée comme un problème inverse mal-posé et mal-conditionné), en considérant particulièrement les systèmes SIMO. Dans un premier temps une technique d’identification aveugle de ce système où l’ordre du canal est inconnu (surestimé) est introduite. Nous introduisons d’abord une version simplifiée à coût réduit SCR de la méthode des relations croisées (CR). Ensuite, une version robuste R-SCR basée sur la recherche d’une solution parcimonieuse minimisant la fonction de coût CR est proposée. La restauration d’image est ensuite assurée par une nouvelle approche inspirée des techniques de décodage des signaux 1D et étendue ici aux cas de la restauration d’images en se basant sur une recherche arborescente efficace (algorithme ‘Stack’). Plusieurs améliorations de la méthode ‘Stack’ ont été introduites afin de réduire sa complexité et d’améliorer la qualité de restauration lorsque les images sont fortement bruitées. Ceci en utilisant une technique de régularisation et une approche d’optimisation all-at-once basée sur la descente du gradient qui permet de raffiner l’image estimée et mieux converger vers la solution optimale. Ensuite, les mesures de la qualité d’images sont utilisées comme fonctions de coûts (intégrées dans le critère global) et ce afin d’étudier leur potentiel pour améliorer les performances de restauration. Dans le contexte où l’image d’intérêt est corrompue par d’autres images interférentes, sa restauration nécessite le recours aux techniques de séparation aveugle de sources. Pour cela, une étude comparative de certaines techniques de séparation basées sur la propriété de décorrélation au second ordre et la parcimonie est réalisée. / This thesis concerns the blind restoration of images (formulated as an ill-posed and illconditioned inverse problem), considering a SIMO system. Thus, a blind system identification technique in which the order of the channel is unknown (overestimated) is introduced. Firstly, a simplified version at reduced cost SCR of the cross relation (CR) method is introduced. Secondly, a robust version R-SCR based on the search for a sparse solution minimizing the CR cost function is proposed. Image restoration is then achieved by a new approach (inspired from 1D signal decoding techniques and extended here to the case of 2D images) based on an efficient tree search (Stack algorithm). Several improvements to the ‘Stack’ method have been introduced in order to reduce its complexity and to improve the restoration quality when the images are noisy. This is done using a regularization technique and an all-at-once optimization approach based on the gradient descent which refines the estimated image and improves the algorithm’s convergence towards the optimal solution. Then, image quality measurements are used as cost functions (integrated in the global criterion), in order to study their potential for improving restoration performance. In the context where the image of interest is corrupted by other interfering images, its restoration requires the use of blind sources separation techniques. In this sense, a comparative study of some separation techniques based on the property of second-order decorrelation and sparsity is performed.