Orientador: Yuzo Iano / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Eletrica e de Computação / Made available in DSpace on 2018-08-12T14:35:59Z (GMT). No. of bitstreams: 1 Higa_RogerioSeiji_M.pdf: 2694908 bytes, checksum: 4f1722cc06ee38d8d637afcc25ae51db (MD5) Previous issue date: 2008 / Resumo: A animação é muito utilizada na área cinematográfica para produzir efeitos visuais ou para fazer filmes inteiros. Nessa área, a busca por novas ferramentas caminha junto com a necessidade da indústria do entretenimento de sempre mostrar novidades. Tentando suprir essa demanda, este trabalho propõe uma nova ferramenta que mistura o morphing de imagens, já muito utilizado nesta área, com a média morfológica. O uso dessas duas técnicas permite a geração de uma seqüência de imagens diferente de outras técnicas de morphing. Além disso, também é proposta a utilização de um algoritmo de interpolação de formas, que é utilizado junto ao morphing para interpolar os seus marcadores de atributos. O uso da interpolação de formas permite que dois marcadores correspondentes tenham um número diferente de pontos, e também adiciona opções de compensação de rotação entre as formas dos marcadores. Neste trabalho são mostrados os resultados obtidos com o método proposto. / Abstract: Animation is used in the cinema industry to produce visual effects or entire movies. In this area, the search for new tools comes along with the need of the entertainment industry to show new stuff all the time. To fulfill this need, this work proposes a new tool that blends the image morphing, a famous tool for visual effects, with the morphological median. The use of these two techniques provides an image sequence that's distinct from other similar tools. It is also proposed in this work the use of the shape interpolation which is used in the morphing algorithm to interpolate the features markers. The shape interpolation algorithm allows that the corresponding markers have a different number of points, it also includes a rotation compensation options for the interpolation of the shapes of the markers. In this work are shown the results obtained form the proposed method. / Mestrado / Telecomunicações e Telemática / Mestre em Engenharia Elétrica

Le processus de discrétisation faisant inévitablement appel à des capteurs, et ceux-ci étant limités de par leur nature, de nombreux effets secondaires apparaissent alors lors de ce processus; en particulier, nous perdons la propriété d'être "bien-composé" dans le sens où deux objects discrétisés peuvent être connectés ou non en fonction de la connexité utilisée dans l'image discrète, ce qui peut amener à des ambigüités. De plus, les images discrétisées sont des tableaux de valeurs numériques, et donc ne possèdent pas de topologie par nature, contrairement à notre modélisation usuelle du monde en mathématiques et en physique. Perdre toutes ces propriétés rend difficile l'élaboration d'algorithmes topologiquement corrects en traitement d'images: par exemple, le calcul de l'arbre des formes nécessite que la representation d'une image donnée soit continue et bien-composée; dans le cas contraire, nous risquons d'obtenir des anomalies dans le résultat final. Quelques representations continues et bien-composées existent déjà, mais elles ne sont pas simultanément n-dimensionnelles et auto-duales. La n-dimensionalité est cruciale sachant que les signaux usuels sont de plus en plus tridimensionnels (comme les vidéos 2D) ou 4-dimensionnels (comme les CT-scans). L'auto-dualité est nécéssaire lorsqu'une même image contient des objets a contrastes divers. Nous avons donc développé une nouvelle façon de rendre les images bien-composées par interpolation de façon auto-duale et en n-D; suivie d'une immersion par l'opérateur span, cette interpolation devient une représentation auto-duale continue et bien-composée du signal initial n-D. Cette représentation bénéficie de plusieurs fortes propriétés topologiques: elle vérifie le théorème de la valeur intermédiaire, les contours de chaque coupe de la représentation sont déterminés par une union disjointe de surfaces discrète, et ainsi de suite / Digitization of the real world using real sensors has many drawbacks; in particular, we loose ``well-composedness'' in the sense that two digitized objects can be connected or not depending on the connectivity we choose in the digital image, leading then to ambiguities. Furthermore, digitized images are arrays of numerical values, and then do not own any topology by nature, contrary to our usual modeling of the real world in mathematics and in physics. Loosing all these properties makes difficult the development of algorithms which are ``topologically correct'' in image processing: e.g., the computation of the tree of shapes needs the representation of a given image to be continuous and well-composed; in the contrary case, we can obtain abnormalities in the final result. Some well-composed continuous representations already exist, but they are not in the same time n-dimensional and self-dual. n-dimensionality is crucial since usual signals are more and more 3-dimensional (like 2D videos) or 4-dimensional (like 4D Computerized Tomography-scans), and self-duality is necessary when a same image can contain different objects with different contrasts. We developed then a new way to make images well-composed by interpolation in a self-dual way and in n-D; followed with a span-based immersion, this interpolation becomes a self-dual continuous well-composed representation of the initial n-D signal. This representation benefits from many strong topological properties: it verifies the intermediate value theorem, the boundaries of any threshold set of the representation are disjoint union of discrete surfaces, and so on

Schistosoma mansoni é o parasita causador da esquistossomose mansônica que, de acordo com o Ministério da Saúde do Brasil, afeta atualmente vários milhões de pessoas no país. Uma das formas de diagnóstico da esquistossomose é a detecção de ovos do parasita através da análise de lâminas microscópicas com material fecal. Esta tarefa é extremamente cansativa, principalmente nos casos de baixa endemicidade, pois a quantidade de ovos é muito pequena. Nesses casos, uma abordagem computacional para auxílio na detecção de ovos facilitaria o trabalho de diagnóstico. Os ovos têm formato ovalado, possuem uma membrana translúcida, apresentam uma espícula e sua cor é ligeiramente amarelada. Porém nem todas essas características são observadas em todos os ovos e algumas delas são visíveis apenas com uma ampliação adequada. Além disso, o aspecto visual do material fecal varia muito de indivíduo para indivíduo em termos de cor e presença de diversos artefatos (tais como partículas que não são desintegradas pelo sistema digestivo), tornando difícil a tarefa de detecção dos ovos. Neste trabalho investigamos, em particular, o problema de detecção das linhas que contornam a borda de vários dos ovos. Propomos um método composto por duas fases. A primeira fase consiste na detecção de estruturas do tipo linha usando operadores morfológicos. A detecção de linhas é dividida em três etapas principais: (i) realce de linhas, (ii) detecção de linhas, e (iii) refinamento do resultado para eliminar segmentos de linhas que não são de interesse. O resultado dessa fase é um conjunto de segmentos de linhas. A segunda fase consiste na detecção de subconjuntos de segmentos de linha dispostos em formato elíptico, usando um algoritmo baseado na transformada Hough. As elipses detectadas são fortes candidatas a contorno de ovos de S. mansoni. Resultados experimentais mostram que a abordagem proposta pode ser útil para compor um sistema de auxílio à detecção dos ovos. / Schistosoma mansoni is one of the parasites which causes schistosomiasis. According to the Brazilian Ministry of Health, several million people in the country are currently affected by schistosomiasis. One way of diagnosing it is by egg identification in stool. This task is extremely time-consuming and tiring, especially in cases of low endemicity, when only few eggs are present. In such cases, a computational approach to help the detection of eggs would greatly facilitate the diagnostic task. Schistosome eggs present oval shape, have a translucent membrane and a spike, and their color is slightly yellowish. However, not all these features are observed in every egg and some of them are visible only with an adequate microscopic magnification. Furthermore, the visual aspect of the fecal material varies widely from person to person in terms of color and presence of different artifacts (such as particles which are not disintegrated by the digestive system), making it difficult to detect the eggs. In this work we investigate the problem of detecting lines which delimit the contour of the eggs. We propose a method comprising two steps. The first phase consists in detecting line-like structures using morphological operators. This line detection phase is divided into three steps: (i) line enhancement, (ii) line detection, and (iii) result refinement in order to eliminate line segments that are not of interest. The output of this phase is a set of line segments. The second phase consists in detecting subsets of line segments arranged in an elliptical shape, using an algorithm based on the Hough transform. Detected ellipses are strong candidates to contour of S. mansoni eggs. Experimental results show that the proposed approach has potential to be effectively used as a component in a computer system to help egg detection.

Esta dissertação apresenta um novo método de segmentação de movimento baseado na obtenção dos contornos e em filtros morfológicos. A nova técnica apresenta vantagens em relação ao número de falsos positivos e falsos negativos em situações específicas quando comparada às técnicas tradicionais. / This work presents a novel motion segmentation technique based in contours and in morphological filters. It presents advantages in the number of false positives and false negatives in some situations when compared to the classic techniques.

This work deals with methods of segmentation of biomedical image signals. It describes, sums up and compares representative methods of digital image processing. Segmentation based on parametric representation is one of the mentioned methods. So as the basic parameter can be chosen for example luminance and the final binary image is obtained by thresholding. Next described method is segmentation based on edge representation. This method can be divided into edge detection by the help of edge detectors and of Hough transformation. Edge detectors work with the first and second derivation. The following method is region-based segmentation, which can be used for a image with noise. This category can be divided into three parts. The first one is segmentation via splitting and merging regions, when the image is split and the created regions are tested on a defined condition. If the condition is satisfied, the region merges and doesn’t continue splitting. The second one is region growing segmentation, when adjacent pixels with a similar intensity of luminance are grouped together and create a segmentated region. Third one is watershed segmentation algorithm based on the idea of water diffusion on uneven surface. The last group of methods is segmentation via flexible and active contours. Here is described an active shape model proceeding from a possibility to deform models so that they match with sample shapes. Next I also describe method Snakes, where occurs gradual contour shaping up to the edge of the object in the image. For the final editing is used mathematical morphology of segmentated images. I aimed to meet methods of image signals segmentation, to cover the chosen methods as a script in programming language Matlab and to check their properties on images.

Dans ce travail, nous étudions le cadre de la morphologie mathématique sur les complexes simpliciaux. Complexes simpliciaux sont une structure versatile et largement utilisée pour représenter des données multidimensionnelles, telles que des maillages, qui sont des complexes tridimensionnels, ou des graphes, qui peuvent être interprétées comme des complexes bidimensionnels. La morphologie mathématique est l'un des cadres les plus puissants pour le traitement de l'image, y compris le traitement des structures numériques, et est largement utilisé pour de nombreuses applications. Toutefois, les opérateurs de morphologie mathématique sur des espaces complexes simpliciaux n'est pas un concept entièrement développé dans la littérature. Dans ce travail, nous passons en revue certains opérateurs classiques des complexes simpliciaux sous la lumière de la morphologie mathématique, de montrer qu'ils sont des opérateurs de morphologie. Nous définissons certains treillis de base et les opérateurs agissant sur ces treillis: dilatations, érosions, ouvertures, fermetures et filtres alternés séquentiels, et aussi leur extension à simplexes pondérés. Cependant, les principales contributions de ce travail sont ce que nous appelions les opérateurs dimensionnels, petites et polyvalents opérateurs qui peuvent être utilisés pour définir de nouveaux opérateurs sur les complexes simpliciaux, qui garde les propriétés de la morphologie mathématique. Ces opérateurs peuvent également être utilisés pour exprimer pratiquement n'importe quel opérateur dans la littérature. Nous illustrons les opérateurs définis et nous comparons les filtres alternés séquentiels contre filtres définis dans la littérature, où nos filtres présentent de meilleurs résultats pour l'enlèvement du petit, intense bruit des images binaires / In this work we study the framework of mathematical morphology on simplicial complex spaces. Simplicial complexes are a versatile and widely used structure to represent multidimensional data, such as meshes, that are tridimensional complexes, or graphs, that can be interpreted as bidimensional complexes. Mathematical morphology is one of the most powerful frameworks for image processing, including the processing of digital structures, and is heavily used for many applications. However, mathematical morphology operators on simplicial complex spaces is not a concept fully developped in the literature. In this work, we review some classical operators from simplicial complexes under the light of mathematical morphology, to show that they are morphology operators. We define some basic lattices and operators acting on these lattices: dilations, erosions, openings, closings and alternating sequential filters, including their extension to weighted simplexes. However, the main contributions of this work are what we called dimensional operators, small, versatile operators that can be used to define new operators on simplicial complexes, while mantaining properties from mathematical morphology. These operators can also be used to express virtually any operator from the literature. We illustrate all the defined operators and compare the alternating sequential filters against filters defined in the literature, where our filters show better results for removal of small, intense, noise from binary images

L'extension de la morphologie mathématique au domaine de la couleur ou du multi/hyperspectral en traitement et analyse d'images n'est pas élémentaire. La majorité des approches se sont focalisées sur la formulation mathématique des opérateurs sans prendre en compte le sens physique ou perceptuel de l'information couleur/spectrale.Les outils développés dans ce travail s'inscrivent dans un nouveau formalisme générique basé sur une fonction de distance. Cette construction permet d'utiliser les opérateurs morphologiques dans le domaine de la couleur ou du multi/hyperspectral en adaptant la fonction de distance. De plus, le choix de la fonction de distance rend les opérateurs valides au sens de la perception ou de la physique.Face aux nombre croissant d'approches existantes, des critères de sélection ont été développés afin de les comparer les différentes écritures de morphologie mathématique. Ces critères sont basés sur le respect des propriétés théoriques des opérateurs, sur les propriétés métrologiques et sur l'efficacité numérique.Grâce à un formalisme prenant en compte l'information perceptuelle de la couleur et intégrant une définition valide des éléments structurants non-plats, deux types d'opérateurs de plus haut niveau ont été définis. Le premier est un détecteur d'objets spatio-colorimétrique passant par la définition d'un gabarit spatial et vectoriel. Le second, est le calcul de spectres de textures vectoriels. L'extension des deux propos au spectral a été réalisé et ouvre de nouvelles questions scientifiques. / Mathematical morphology extension to colour or multi/hyperspectral domain in image processing is not straightforward. Most approaches have focused on the mathematical translation of the operators without taking into account the physical or perceptual sense of colour/spectral information. The developed tools in this work are part of a new generic formalism based on adistance function. This construction allows using morphological operators in colour or multi/hyperspectral domain by adapting the distance function. Moreover, the distance function choice validates the operators in the perceptual or physical sense.In front of the increasing number of existing approaches, selection criteria are developed in order to compare the different mathematical morphology constructions. These criteria are based on the validation of the theoretical properties of operators, on the metrological properties and the computational efficiency.With a formalism taking into account the perceptual information of colour and integrating a valid defnition of non-flat structuring elements, two kinds of highest level operators are defned. The frst is a spatial-colorimetric object detector through the defnition of a vectorial and spacial template. The second is the computation of vectorial texture spectra. The spectral extension for both tools is made and opens new scientifc questions.

Grâce aux informations spatiales et spectrales qu'elle apporte, l'imagerie multispectrale de la peau est devenue un outil incontournable de la dermatologie. Cette thèse a pour objectif d'évaluer l’intérêt de cet outil pour la cosmétologie à travers trois études : la détection d'un fond de teint, l'évaluation de l'âge et la mesure de la rugosité.Une base d'images multispectrales de peau est construite à l'aide d'un système à multiples filtres optiques. Une phase de prétraitement est nécessaire à la standardisation et à la mise en valeur de la texture des images.Les matrices de covariance des acquisitions peuvent être représentées dans un espace multidimensionnel, ce qui constitue une nouvelle approche de visualisation de données multivariées. De même, une nouvelle alternative de réduction de la dimensionnalité basée sur l'ACP est proposée dans cette thèse. L'analyse approfondie de la texture des images multispectrales est réalisée : les paramètres de texture issus de la morphologie mathématique et plus généralement de l'analyse d'images sont adaptés aux images multivariées. Dans cette adaptation, plusieurs distances spectrales sont expérimentées, dont une distance intégrant le modèle LIP et la métrique d'Asplünd.Les résultats des prédictions statistiques générées à partir des données de texture permettent de conclure quant à la pertinence du traitement des données et de l'utilisation de l'imagerie multispectrale pour les trois études considérées. / Thanks to its precision in spatial and spectral domain, multispectral imaging has become an essential tool in dermatology. This thesis focuses on the interest of this technology for cosmetological parameters assessment through three different studies: the detection of a foundation make-up, age assessment and roughness measurement.A database of multispectral skin images is build using a multiple optical filters system. A preprocessing step allows to standardize those texture images before their exploitation.Covariance matrices of mutispectral acquisitions can be displayed in a multidimensional scaling space which is a novel way to represent multivariate data sets. Likewise, a new dimensionality reduction algorithm based on PCA is proposed in this thesis.A complete study of the images texture is performed: texture features from mathematical morphology and more generally from image analysis are expanded to the case of multivariate images. In this process, several spectral distances are tested, among which a new distance associating the LIP model to the Asplund metric.Statistical predictions are generated from texture data. Thoses predictions lead to a conclusion about the data processing efficiency and the relevance of multispectral imaging for the three cosmetologic studies.

La morphologie mathématique est une théorie puissante pour l’analyse d’images 2 D. Elle se base sur la dilatation et l’érosion, qui correspondent à l’addition et la soustraction de Minkowski. Afin d’analyser des maillages 3D par morphologie mathématique, on doit disposer d’algorithmes performants et robustes pour le calcul exact de l’addition et de la soustraction pour ces maillages. Malheureusement, les travaux existants sont, soit approximés, soit non robustes ou limités par des contraintes. Aucun travail n’a traité la différence. Ces difficultés sont dues au fait qu’un maillage représente une surface linéaire par morceaux englobant un ensemble contenu et non dénombrable. Nous avons introduit la notion de sommets contributeurs et nous avons développé un algorithme efficace et robuste pour le calcul de la somme de polyèdres convexes. Nous l’avons par la suite adapté et proposé deux algorithmes performants pour la somme d’une paire de polyèdres non convexe/convexe, tout en gérant correctement les polyèdres complexes, les situations de non-variété ainsi que les changements topologiques. Nous avons également démontré la dualité des sommets contributeurs et nous l’avons exploité pour développer la première approche du calcul exact et efficace de la différence de polyèdres convexes. La dualité des sommets contributeurs ainsi que la robustesse et l’efficacité de nos approches motivent le développement d’une approche unifiée pour l’addition et la soustraction de polyèdres quelconques, ce qui permettra d’appliquer des traitements morphologiques à des maillages 3D. D’autres domaines tels que l’imagerie médicale, la robotique, la géométrie ou la chimie pourront en tirer profit / Mathematical morphology is a powerful theory for the analysis of 2D digital images. It is based on dilation and erosion, which correspond to Minkowski addition and subtraction. To be able to analyze 3D meshes using mathematical morphology, we must use efficient and robust algorithms for the exact computation of the addition and subtraction of meshes. Unfortunately, existing approaches are approximated, non-robust or limited by some constraints. No work has addressed the difference. These difficulties come from the the fact that a mesh represents a piecewise linear surface bounding a continuous and uncountable set. We introduced the concept of contributing vertices and developed an efficient and robust algorithm for the computation of the Minkowski sum of convex polyhedra. After that, we adapted and proposed two efficient algorithms for the computation of the Minkowski sum of a non-convex/convex pair of polyhedra, while properly handling complex polyhedra, non-manifold situations and topological changes. We also demonstrated the duality of the contributing vertices concept and exploited it to develop the first approach for the efficient and exact computation of the Minkowski difference of convex polyhedra. The duality of the contributing vertices concept as well as the robustness and efficiency of our approaches motivate the development of a unified approach for the Minkowski addition and subtraction of arbitrary polyhedral, which will permit the morphological analysis of 3D meshes. Other areas such as medical imaging, robotics, geometry or chemistry may benefit from our approaches

Resolver um problema de processamento de imagens pode ser uma tarefa bastante complexa. Em geral, isto depende de diversos fatores, como o conhecimento, experiência e intuição de um especialista, e o conhecimento do domínio da aplicação em questão. Motivados por tal complexidade, alguns grupos de pesquisa têm trabalhado na criação de técnicas para projetar operadores de imagens automaticamente, a partir de uma coleção de exemplos de entrada e saída do operador desejado. A abordagem multirresolução tem sido empregada com sucesso no projeto estatístico de W-operadores de janelas grandes. Esta metodologia usa uma estrutura piramidal de janelas para auxiliar na estimação das distribuições de probabilidade condicional para padrões não observados no conjunto de treinamento. No entanto, a qualidade do operador projetado depende diretamente da pirâmide escolhida. Tal escolha é feita pelo projetista a partir de sua intuição e de seu conhecimento prévio sobre o problema. Neste trabalho, investigamos o uso da entropia condicional como um critério para determinar automaticamente uma boa pirâmide a ser usada no projeto do W-operador. Para isto, desenvolvemos uma técnica que utiliza o arcabouço piramidal multirresolução como um modelo na estimação da distribuição conjunta de probabilidades. Experimentos com o problema de reconhecimento de dígitos manuscritos foram realizados para avaliar o desempenho do método. Utilizamos duas bases de dados diferentes, com bons resultados. Além disso, outra contribuição deste trabalho foi a experimentação com mapeamentos de resolução da teoria de pirâmides de imagens no contexto do projeto de W-operadores multirresolução. / The task of finding a good solution for an image processing problem is often very complex. It usually depends on the knowledge, experience and intuition of an image processing specialist. This complexity has served as a motivation for some research groups to create techniques for automatically designing image operators based on a collection of input and output examples of a desired operator. The multiresolution approach has been successfully used to statistically design W-operators for large windows. However, the success of this method directly depends on the adequate choice of a pyramidal window structure, which is used to aid in the estimation of the conditional probability distributions for patterns that do not appear in the training set. The choice is made by the designer, based on his intuition and previous knowledge of the problem domain. In this work, we investigate the use of the conditional entropy criterion for automatically determining a good pyramid. In order to compute the entropy, we have developed a technique that uses the multiresolution pyramidal framework as a model in the estimation of the joint probability distribution. The performance of the method is evaluated on the problem of handwritten digits recognition. Two different databases are used, with good practical results. Another important contribution of this work is the experimentation with resolution mappings from image pyramids theory in the context of multiresolution W-operator design.