Made available in DSpace on 2016-06-02T19:06:20Z (GMT). No. of bitstreams: 1 6519.pdf: 3957893 bytes, checksum: 94ee475c0b2df3476b88d3f2c25f3512 (MD5) Previous issue date: 2014-03-14 / When working with binary images, mathematical morphology provides powerful tools for analyzing them. Along with genetic algorithms, it allows various computational tasks that are performed autonomously. In recent decades, the decomposition of structuring elements has been involved in the morphological operations used to reduce the degree of difficulty imposed by images of larger size implying in the efficiency of the hardware used for the processing of such images. For accelerating this process, this master's project uses MATLAB and Visual Studio as development tools, aiming at developing an efficient algorithm for decomposing the structuring element facilitating a possible hardware implementation with aim of decreasing the time waste in processing those images. / Ao trabalhar com imagens binárias, a morfologia matemática oferece ferramentas eficientes para análise das mesmas. Juntamente com algoritmos genéticos, permitem que sejam executadas de forma autônoma diversas tarefas computacionais. Nas últimas décadas tem-se utilizado a decomposição dos elementos estruturantes envolvidos nas operações morfológicas para diminuir o grau de dificuldade imposto por imagens de tamanho elevado implicando na eficiência do hardware utilizado para o processamento de tais imagens. Para acelerar esse processo, este trabalho de mestrado, utiliza os softwares MATLAB e Visual Studio como ferramentas de desenvolvimento, tendo como objetivo elaborar um algoritmo eficiente de decomposição do elemento estruturante facilitando uma possível aplicação em hardware, diminuindo ainda mais o tempo gasto no processamento de imagens.

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Neste trabalho são apresentados os resultados obtidos com a quantificação de parâmetros - por meio de técnicas de histomorfometria - de amostras de espumas cerâmicas. Esta quantificação foi feita por meio de análise de imagens bidimensionais a partir de técnicas de processamento de imagens digitais. As imagens analisadas neste trabalho foram obtidas através de digitalização das faces das amostras com o uso de um scanner convencional e os dados obtidos para cada amostra de espuma foram comparados com os resultados encontrados com a utilização de imagens tomográficas e um aplicativo desenvolvido para a análise de tais imagens. Os ensaios realizados com as amostras citadas mostram que a utilização do scanner convencional para a aquisição das imagens é vantajosa sob o ponto de vista da facilidade de obtenção de tais imagens e que a quantificação histomorfométrica pode ser feita a partir de imagens 2D desses objetos. / In this work will present the results obtained with quantification of parameters by means of histomorphometry techniques of ceramic foam samples. This quantification was done by means of two-dimensional image analysis techniques from image processing. The images analyzed in this work were obtained by scanning the faces of the samples using a conventional scanner and the data obtained for each sample were compared with results obtained by use of tomographic images and an application developed for the analysis of such images. Tests conducted whit the samples mentioned show the use of conventional scanner for image acquisition is advantageous from the point of view of obtaining such images and the histomorphometric quantification can be made in 2D images of the faces of these objects.

Através das imagens de fundo do olho, os especialistas em oftalmologia podem detectar possíveis complicações relacionadas ao Diabetes como a diminuição ou até a perda da capacidade de visão. O Edema Macular Diabético (EMD) é uma das complicações que lideram os casos de danos à visão em pessoas em idade de trabalho. Sendo assim, esta tese apresenta métodos para automaticamente identificar os diferentes níveis de gravidade do Edema Macular Diabético visando auxiliar o especialista no diagnóstico dessa patologia. Como resultado final, propõe-se automaticamente e rapidamente identificar, a partir da imagem, se o paciente possui o EMD leve, moderado ou grave. Utilizando imagens de fundo do olho de um banco de dados livremente disponível na internet (ou seja, o DIARETDB1), o método proposto para a identificação automática do EMD obteve uma precisão de 94,29%. Alguns métodos intermediários necessários para a solução desse problema foram propostos e os resultados publicados na literatura científica. / Through color eye fundus images, the eye care specialists can detect possible complications related to diabetes as the vision impairment or vision loss. The Diabetic Macular Edema (DME) is the most common cause of vision damage in working-age people. Therefore, this thesis presents an approach to automatically identify the different levels of severity of diabetic macular edema aiming to assist the expert in the diagnosis of this pathology. As a final result, a methodology to automatically and quickly identify, from the eye fundus image, if a patient has the EMD mild, moderate or severe EMD is proposed. In a preliminary evaluation of our DME grading scheme using publicly available eye fundus images (i.e., DIARETDB1 image database), an accuracy of 94.29% was obtained. Some intermediate methods needed to solve this problem have been proposed and the results published in scientific literature.

Através das imagens de fundo do olho, os especialistas em oftalmologia podem detectar possíveis complicações relacionadas ao Diabetes como a diminuição ou até a perda da capacidade de visão. O Edema Macular Diabético (EMD) é uma das complicações que lideram os casos de danos à visão em pessoas em idade de trabalho. Sendo assim, esta tese apresenta métodos para automaticamente identificar os diferentes níveis de gravidade do Edema Macular Diabético visando auxiliar o especialista no diagnóstico dessa patologia. Como resultado final, propõe-se automaticamente e rapidamente identificar, a partir da imagem, se o paciente possui o EMD leve, moderado ou grave. Utilizando imagens de fundo do olho de um banco de dados livremente disponível na internet (ou seja, o DIARETDB1), o método proposto para a identificação automática do EMD obteve uma precisão de 94,29%. Alguns métodos intermediários necessários para a solução desse problema foram propostos e os resultados publicados na literatura científica. / Through color eye fundus images, the eye care specialists can detect possible complications related to diabetes as the vision impairment or vision loss. The Diabetic Macular Edema (DME) is the most common cause of vision damage in working-age people. Therefore, this thesis presents an approach to automatically identify the different levels of severity of diabetic macular edema aiming to assist the expert in the diagnosis of this pathology. As a final result, a methodology to automatically and quickly identify, from the eye fundus image, if a patient has the EMD mild, moderate or severe EMD is proposed. In a preliminary evaluation of our DME grading scheme using publicly available eye fundus images (i.e., DIARETDB1 image database), an accuracy of 94.29% was obtained. Some intermediate methods needed to solve this problem have been proposed and the results published in scientific literature.

Orientador: Peter Sussner / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Matemática, Estatística e Computação Científica / Made available in DSpace on 2018-08-16T05:02:12Z (GMT). No. of bitstreams: 1 Esmi_Estevao_M.pdf: 1708768 bytes, checksum: 81d1d15b597bdc13e41b87c4847aa2f7 (MD5) Previous issue date: 2010 / Resumo: Redes neurais morfológicas (MNN) são redes neurais artificiais cujos nós executam operações elementares da morfologia matemática (MM). Vários modelos de MNNs e seus respectivos algoritmos de treinamentos têm sido propostos nos últimos anos, incluindo os perceptrons morfológicos(MPs), o perceptron morfológico com dendritos, as memórias associativas morfológicas (fuzzy), as redes neurais morfológicas modulares e as redes neurais de pesos compartilhados e regularizados. Aplicações de MNNs incluem reconhecimento de padrão, previsão de séries temporais, detecção de alvos, auto-localização e processamento de imagens hiperespectrais. Nesta tese, abordamos dois novos modelos de redes neurais morfológicas.O primeiro consiste em uma memória associativa fuzzy denominada KS-FAM, e o segundo representa uma nova versão do perceptron morfológico para problemas de classificação de múltiplas classes, denominado perceptron morfológico com aprendizagem competitiva(MP/CL). Para ambos modelos, investigamos e demonstramos várias propriedades. Em particular para a KS-FAM, caracterizamos as condições para que uma memória seja perfeitamente recordada, assim como a formada saída produzida ao apresentar um padrão de entrada qualquer. Provamos ainda que o algoritmo de treinamento do MP/CL converge em um número finito de passos e que a rede produzida independe da ordem com que os padrões de treinamento são apresentados. Além disso, é garantido que o MP/CL resultante classifica perfeitamente todos os dados de treinamento e não produz regiões de indecisões. Finalmente, comparamos os desempenhos destes modelos com os de outros modelos similares em uma série de experimentos, que incluir e conhecimento de imagens em tons de cinza, para a KS-FAM, e classificação de vários conjuntos de dados disponíveis na internet, para o MP/CL / Abstract: Morphological neural networks (MNN) are artificial neural networks whose hidden neurons perform elementary operations of mathematical morphology (MM). Several particular models of MNNs have been proposed in recent years, including morphological perceptrons (MPs), morphological perceptrons with dendrites, (fuzzy) morphological associative memories, modular morphological neural networks as well as morphological shared-weight and regularization neural networks. Applications of MNNs include pattern recognition, time series prediction, target detection, self-location, and hyper-spectral image processing. In this thesis, we present two new models of morphological neural networks. The first one consists of a fuzzy associative memory called KS-FAM. The second one represents a novel version of the morphological perceptron for classification problems with multiple classes called morphological perceptron with competitive learning(MP/CL). For both KS-FAM and MP/CL models, we investigated and showed several properties. In particular, we characterized the conditions for perfect recall using the KS-FAM as well as the outputs produced upon presentation of an arbitrary input patern. In addition, we proved that the learning algorithm of the MP/CL converges in a finite number of steps and that the results produced after the conclusion of the training phase do not depend on the order in which the training patterns are presented to the network. Moreover, the MP/CL is guaranteed to perfectly classify all training data without generating any regions of indecision. Finaly, we compared the performances of our new models and a range of competing models in terms of a series of experiments in gray-scale image recognition (in case of the KS-FAM) and classification using several well-known datasets that are available on the internet (in case of the MP/CL) / Mestrado / Matematica Aplicada / Mestre em Matemática Aplicada

Orientador: Roberto de Alencar Lotufo / Tese (doutorado) - Universidade Estadual de Campinas, Faculdade de Engenharia Eletrica e de Computação / Made available in DSpace on 2018-08-14T21:44:46Z (GMT). No. of bitstreams: 1 Silva_AlexandreGoncalves_D.pdf: 8468020 bytes, checksum: 8e00e5b8cd107e6379773db874c73089 (MD5) Previous issue date: 2009 / Resumo: Uma imagem em níveis de cinza pode ser interpretada como uma superfície topográfica e representada por uma árvore de componentes, baseada na relação de inclusão de regiões conexas, obtida a partir da decomposição por limiares. Medidas sobre platôs, vales ou montanhas deste relevo são úteis na caracterização de objetos de interesse em sistemas de visão computacional. Este trabalho apresenta métodos de filtragem, segmentação e reconhecimento de padrões derivados da exploração de aspectos semânticos oferecidos por essa estrutura hierárquica, construída de maneira concisa e em tempo quase-linear, mesmo com a introdução de uma série de novos atributos geométricos, topológicos e estatísticos. Havendo menos elementos a processar em relação à quantidade de pixels e, sendo possível a alteração da organização dos mesmos por meio de podas e enxertos, essa representação possibilita a implementação de algoritmos rápidos para operadores conexos antiextensivos. Um importante resultado da árvore estendida de atributos é a formulação genérica e determinação eficiente de novos valores de extinção, utilizados como modelo simplificado de seleção de extremos ou marcadores relevantes para reconstrução morfológica ou segmentação por regiões de influência. Propõe-se também um algoritmo unificado para pesquisa de formas conforme a análise adotada para verificação aproximada da disposição espacial de pixels de cada componente na árvore. / Abstract: A gray-level image can be interpreted as a topographical surface and represented by a component tree, based on the inclusion relation of connected regions, obtained by threshold decomposition. Measures on plateaus, valleys or mountains of this relief are useful in the characterization of objects of interest in computer vision systems. This work presents filtering, segmentation and pattern recognition methods from the exploration of semantic aspects provide by this hierarchical structure, whose can be constructed in a concise way and in quasi-linear time, even with the addition of a set of new geometric, topological and statistical attributes. How there is less elements to process in relation to the amount of pixels, and being able to change the organization of these through pruning and grafting, this representation allows the implementation of fast algorithms for connected anti-extensive operators. An important result of the extended attribute tree is the generic formulation and efficient determination of new extinction values, used as simplified model of selecting relevant extremes or markers for morphological reconstruction or segmentation by influence regions. A unified algorithm to search shapes is also proposed according the analysis adopted for approximate verification of the spatial layout of pixels of each component in the tree. / Doutorado / Engenharia de Computação / Doutor em Engenharia Elétrica

Les plus grandes villes au monde disposent de plans 2D très détaillés des rues et des espaces publics. Ces plans contiennent des informations relatives aux routes, trottoirs, façades et objets urbains tels que, entre autres, les lampadaires, les panneaux de signalisation, les poteaux, et les arbres.De nos jours, certaines autorités locales, agences nationales de cartographie et sociétés privées commencent à adjoindre à leurs cartes de villes des informations en 3D, des choix de navigation et d'accessibilité.En comparaison des premiers systèmes de scanning en 3D d'il y a 30 ans, les scanners laser actuels sont moins chers, plus rapides et fournissent des nuages de points 3D plus précis et plus denses.L'analyse de ces données est difficile et laborieuse, et les méthodes semi-automatiques actuelles risquent de ne pas être suffisamment précises ni robustes. C'est en ce sens que des méthodes automatiques pour l'analyse urbaine sémantique en 3D sont nécessaires.Cette thèse constitue une contribution au domaine de l'analyse sémantique de nuages de points en 3D dans le cadre d'un environnement urbain.Nos méthodes sont basées sur les images d'élévation et elles illustrent l'efficacité de la morphologie mathématique pour développer une chaîne complète de traitement en 3D, incluant 6 étapes principales:i)~filtrage et pré-traitement;ii)~segmentation du sol et analyse d'accessibilité;iii)~segmentation des façades;iv)~détection d'objets;v)~segmentation d'objets;vi)~classification d'objets.De plus, nous avons travaillé sur l'intégration de nos résultats dans une chaîne de production à grande échelle.Ainsi, ceux-ci ont été incorporés en tant que ``shapefiles'' aux Systèmes d'Information Géographique et exportés en tant que nuages de points 3D pour la visualisation et la modélisation.Nos méthodes ont été testées d'un point de vue qualitatif et quantitatif sur plusieurs bases de données issues de l'état de l'art et du projet TerraMobilita.Nos résultats ont montré que nos méthodes s'avèrent précises, rapides et surpassent les travaux décrits par la littérature sur ces mêmes bases.Dans la conclusion, nous abordons également les perspectives de développement futur. / Most important cities in the world have very detailed 2D urban plans of streets and public spaces.These plans contain information about roads, sidewalks, facades and urban objects such as lampposts, traffic signs, bollards, trees, among others.Nowadays, several local authorities, national mapping agencies and private companies have began to consider justifiable including 3D information, navigation options and accessibility issues into urban maps.Compared to the first 3D scanning systems 30 years ago, current laser scanners are cheaper, faster and provide more accurate and denser 3D point clouds.Urban analysis from these data is difficult and tedious, and existing semi-automatic methods may not be sufficiently precise nor robust.In that sense, automatic methods for 3D urban semantic analysis are required.This thesis contributes to the field of semantic analysis of 3D point clouds from urban environments.Our methods are based on elevation images and illustrate how mathematical morphology can be exploited to develop a complete 3D processing chain including six main steps:i)~filtering and preprocessing;ii)~ground segmentation and accessibility analysis;iii)~facade segmentation,iv)~object detection;v)~object segmentation;and, vi)~object classification.Additionally, we have worked on the integration of our results into a large-scale production chain. In that sense, our results have been exported as 3D point clouds for visualization and modeling purposes and integrated as shapefiles into Geographical Information Systems (GIS).Our methods have been qualitative and quantitative tested in several databases from the state of the art and from TerraMobilita project.Our results show that our methods are accurate, fast and outperform other works reported in the literature on the same databases.Conclusions and perspectives for future work are discussed as well.

Le traitement d'images numériques a suivi l'évolution de l'électronique et de l'informatique. Il est maintenant courant de manipuler des images à valeur non pas dans {0,1}, mais dans des variétés ou des distributions de probabilités. C'est le cas par exemple des images couleurs où de l'imagerie du tenseur de diffusion (DTI). Chaque type d'image possède ses propres structures algébriques, topologiques et géométriques. Ainsi, les techniques existantes de traitement d'image doivent être adaptés lorsqu'elles sont appliquées à de nouvelles modalités d'imagerie. Lorsque l'on manipule de nouveaux types d'espaces de valeurs, les précédents opérateurs peuvent rarement être utilisés tel quel. Même si les notions sous-jacentes ont encore un sens, un travail doit être mené afin de les exprimer dans le nouveau contexte. Cette thèse est composée de deux parties indépendantes. La première, « Morphologie mathématiques pour les images non standards », concerne l'extension de la morphologie mathématique à des cas particuliers où l'espace des valeurs de l'image ne possède pas de structure d'ordre canonique. Le chapitre 2 formalise et démontre le problème de l'irrégularité des ordres totaux dans les espaces métriques. Le résultat principal de ce chapitre montre qu'étant donné un ordre total dans un espace vectoriel multidimensionnel, il existe toujours des images à valeur dans cet espace tel que les dilatations et les érosions morphologiques soient irrégulières et incohérentes. Le chapitre 3 est une tentative d'extension de la morphologie mathématique aux images à valeur dans un ensemble de labels non ordonnés.La deuxième partie de la thèse, « Estimation de densités de probabilités dans les espaces de Riemann » concerne l'adaptation des techniques classiques d'estimation de densités non paramétriques à certaines variétés Riemanniennes. Le chapitre 5 est un travail sur les histogrammes d'images couleurs dans le cadre de métriques perceptuelles. L'idée principale de ce chapitre consiste à calculer les histogrammes suivant une approximation euclidienne local de la métrique perceptuelle, et non une approximation globale comme dans les espaces perceptuels standards. Le chapitre 6 est une étude sur l'estimation de densité lorsque les données sont des lois Gaussiennes. Différentes techniques y sont analysées. Le résultat principal est l'expression de noyaux pour la métrique de Wasserstein. / Digital image processing has followed the evolution of electronic and computer science. It is now current to deal with images valued not in {0,1} or in gray-scale, but in manifolds or probability distributions. This is for instance the case for color images or in diffusion tensor imaging (DTI). Each kind of images has its own algebraic, topological and geometric properties. Thus, existing image processing techniques have to be adapted when applied to new imaging modalities. When dealing with new kind of value spaces, former operators can rarely be used as they are. Even if the underlying notion has still a meaning, a work must be carried out in order to express it in the new context.The thesis is composed of two independent parts. The first one, "Mathematical morphology on non-standard images", concerns the extension of mathematical morphology to specific cases where the value space of the image does not have a canonical order structure. Chapter 2 formalizes and demonstrates the irregularity issue of total orders in metric spaces. The main results states that for any total order in a multidimensional vector space, there are images for which the morphological dilations and erosions are irregular and inconsistent. Chapter 3 is an attempt to generalize morphology to images valued in a set of unordered labels.The second part "Probability density estimation on Riemannian spaces" concerns the adaptation of standard density estimation techniques to specific Riemannian manifolds. Chapter 5 is a work on color image histograms under perceptual metrics. The main idea of this chapter consists in computing histograms using local Euclidean approximations of the perceptual metric, and not a global Euclidean approximation as in standard perceptual color spaces. Chapter 6 addresses the problem of non parametric density estimation when data lay in spaces of Gaussian laws. Different techniques are studied, an expression of kernels is provided for the Wasserstein metric.

Dans cette thèse, nous présentons de nouvelles méthodes de traitement d’images pourextraire ou rehausser les éléments fins d’une image. Pour ces opérateurs, issus de la morphologie mathématique,l’accent a été mis principalement sur la précision de détection et sur le temps de calcul,qui doivent être optimisés pour pouvoir répondre aux contraintes de temps imposées par différentesapplications industrielles. La première partie de ce mémoire présente ces méthodes, organisées enfonction de la tortuosité des objets à détecter. Nous commençons par proposer un algorithme rapidepour le calcul des ouvertures 1-D afin d’extraire des structures rectilignes des images. Puis, nous étudionsune nouvelle classe d’opérateurs rapides avec les ouvertures parcimonieuses par chemins, permettantd’analyser des structures ayant une tortuosité modérée. Enfin, nous proposons de nouveauxéléments structurants adaptatifs et des filtres connexes construits avec des attributs géodésiques etgéométriques pour extraire des structures filiformes ayant une tortuosité quelconque.Dans un second temps, nous avons développé une méthode d’analyse statistique en introduisantune nouvelle pénalisation adaptative. L’objectif consiste à créer un modèle prédictif précis, quiminimise en même temps une fonction de coût, indépendante des données. Lorsque cette fonctionde coût est liée au temps de calcul de chaque descripteur, il est alors possible de créer un modèleparcimonieux précis et qui minimise les temps de calcul. Cette méthode est une généralisation desrégressions linéaires et logistiques Ridge, Forward stagewise, Lar, ou Lasso.Les algorithmes développés dans cette thèse ont été utilisés pour trois applications industrielles,très différentes les unes des autres, mais toutes faisant intervenir une approche multidisciplinaire : letraitement d’images et l’analyse statistique. L’association de ces deux disciplines permet d’améliorerla généricité des stratégies proposées puisque les opérateurs de traitement d’images alliés à un apprentissagesupervisé ou non supervisé, permettent d’adapter le traitement à chaque application.Mots clés : Traitement d’images, morphologie mathématique, analyse statistique, caractérisation deformes, contrôles non destructifs, ouvertures parcimonieuses par chemins, region growing structuringelements, amincissements par attributs géodésiques et topologiques, adaptive coefficient shrinkage. / This PhD is dedicated to new image processing methods to extract or enhance thinobjects from an image. These methods stem from mathematical morphology, and they mainly focuson the accuracy of the detection and on the computation time. This second constraint is imposed bythe fact that we are dealing with high-throughput applications. The first part of this thesis presentsthese methods, organized according to the tortuosity of the objects to detect. We first propose afast algorithm for the computation of 1-D openings, used to extract thin and straight structures in theimages. Then, we study a new class of fast operators, parsimonious path openings, which can extractthin structures with moderate tortuosities. Finally, we propose new adaptive structuring elementsand new thinnings with geodesic and geometric attributes to filter out the noise and to enhance thinstructures of any tortuosity.Besides, we have developed a machine learning method by introducing a new adaptive penalization.We aim at creating a predictive model that minimizes a cost function (independent of the data)while preserving a good accuracy. When this cost function is linked to the computation time of eachfeature, the resulting models will optimize the timings, while preserving a good accuracy. This methodis a generalization of linear and logistic regressions with Ridge, Forward stagewise, Lar or Lassopenalization.The algorithms developed in this thesis have been used for three industrial applications. While theirobjectives are very different, the framework is the same (non-destructive testing) and they all involvea multidisciplinary approach (images processing and statistical analysis). The combination of thesetwo fields yields a higher flexibility in comparison with classical methods. Generic strategies are used,since image processing operators are associated to statistical learning (supervised or unsupervised)to make a specific treatment for each application.Keywords: Image processing, mathematical morphology, statistical analysis, pattern recognition,non destructive testing, parsimonious path openings, region growing structuring elements, geodesicand topologic attributes thinnings, adaptive coefficient shrinkage.

Les images angiographiques sont utilisés pour différentes tâches comme le diagnostique, le suivie de pathologies et la planification d'interventions chirurgicales. Toutefois, en raison du faible ratio signal sur bruit et le contenu complexe des données (informations clairsemées), l'analyse des images angiographiques est une tâche fastidieuse et source d'erreurs. Ces différentes considérations ont motivé le développement de nombreuses techniques d'analyse.Les travaux de cette thèse s'organisent autour de deux axes de recherches : d'une part la segmentation des images angiographiques, et d'autre part la modélisation des réseaux vasculaires cérébraux. En segmentation, l'automatisation induit généralement un coût de calcul élevé, alors que les méthodes interactives sont difficiles à utiliser en raison de la dimension et de la complexité des images. Ces travaux présentent un compromis entre les deux approches, en utilisant le concept de segmentation à base d'exemple. Cette stratégie qui utilise les arbres de coupes de façon non standard,conduit à des résultats satisfaisant, lorsqu'elle est appliqué sur des données d'ARM cérébrales 3D. Les approches existantes, en modélisation, reposent exclusivement sur des informations relatives aux vaisseaux. Ces travaux ont exploré une nouvelle voie, consistant à utiliser à la fois les informations vasculaires et morphologiques ( c-à-d structures cérébrales) pour améliorer la précision et la pertinence des atlas obtenus. Les expériences soulignent des améliorations dans les principales étapes du processus de création de l'atlas impacté par l'utilisation de l'information morphologique. Un exemple d'atlas cérébraux a été réalisé. / Angiographie images are useful data for several tasks, e.g., diagnosis, pathology follow-up or surgery planning. However, due to low SNR (noise,artifacts), and complex semantic content (sparseness), angiographie image analysis is a time consurning and error prone task. These consideration have motivated the development of numerous vesse! filtering, segmentation, or modeling techinques.This thesis is organized around two research areas : the segmentation anù the moùeling. Segmentation of cerebral vascular networks from 3D angiographie data remains a challenge. Automation generally induces a high computational cost and possible errors, white interactive methods are hard to use due to the dimension and the complexity of images. This thesis presents a compromise between both approaches by using the concept of example-based segmentation. This strategy, which uses component-trees in a non-standard fashion, leads to promising results, when applied on cerebral MR angiographie data. The generation of cerebrovascular atlases remains a complex and infrequently considered issue. The existing approaches rely on information exclusively related to the vessels. This thesis investigate a new way, consisting of using both vascular and morphological information (i.e. Cerebral structures) to improve the accuracy and relevance of the obtaines vascular atlases. Experiments emphasize improvments in the main steps of the atlas generation process impacted by the use of the morphological information. An example of cerebrovascular atlas obtained from a dataset of MRAs acquired form different acquisition devices has been provided.