Many computer vision applications such as image filtering, segmentation and stereovision can be formulated as optimization problems. Recently discrete, convex, globally optimal methods have received a lot of attention. Many graph-based methods suffer from metrication artefacts, segmented contours are blocky in areas where contour information is lacking. In the first part of this work, we develop a discrete yet isotropic energy minimization formulation for the continuous maximum flow problem that prevents metrication errors. This new convex formulation leads us to a provably globally optimal solution. The employed interior point method can optimize the problem faster than the existing continuous methods. The energy formulation is then adapted and extended to multi-label problems, and shows improvements over existing methods. Fast parallel proximal optimization tools have been tested and adapted for the optimization of this problem. In the second part of this work, we introduce a framework that generalizes several state-of-the-art graph-based segmentation algorithms, namely graph cuts, random walker, shortest paths, and watershed. This generalization allowed us to exhibit a new case, for which we developed a globally optimal optimization method, named "Power watershed''. Our proposed power watershed algorithm computes a unique global solution to multi labeling problems, and is very fast. We further generalize and extend the framework to applications beyond image segmentation, for example image filtering optimizing an L0 norm energy, stereovision and fast and smooth surface reconstruction from a noisy cloud of 3D points

Biometric systems allow identification of human persons based on physiological or behavioral characteristics, such as voice, handprint, iris or facial characteristics. The use of face and iris recognition as a way to authenticate user’s identities has been a topic of research for years. Present iris recognition systems require that subjects stand close (<2m) to the imaging camera and look for a period of about three seconds until the data are captured. This cooperative behavior is required in order to capture quality images for accurate recognition. This will eventually restrict the amount of practical applications where iris recognition can be applied, especially in an uncontrolled environment where subjects are not expected to cooperate such as criminals and terrorists, for example. For this reason, this thesis develops a collection of methods to deal with low quality face and iris images and that can be applied for face and iris recognition in a non-cooperative environment. This thesis makes the following main contributions: I. For eye and face tracking in low quality images, a new robust method is developed. The proposed system consists of three parts: face localization, eye detection and eye tracking. This is accomplished using traditional image-based passive techniques such as shape information of the eye and active based methods which exploit the spectral properties of the pupil under IR illumination. The developed method is also tested on underexposed images where the subject shows large head movements. II. For iris recognition, a new technique is developed for accurate iris segmentation in low quality images where a major portion of the iris is occluded. Most existing methods perform generally quite well but tend to overestimate the occluded regions, and thus lose iris information that could be used for identification. This information loss is potentially important in the covert surveillance applications we consider in this thesis. Once the iris region is properly segmented using the developed method, the biometric feature information is calculated for the iris region using the relative entropy technique. Iris biometric feature information is calculated using two different feature decomposition algorithms based on Principal Component Analysis (PCA) and Independent Component Analysis (ICA). III. For face recognition, a new approach is developed to measure biometric feature information and the changes in biometric sample quality resulting from image degradations. A definition of biometric feature information is introduced and an algorithm to measure it proposed, based on a set of population and individual biometric features, as measured by a biometric algorithm under test. Examples of its application were shown for two different face recognition algorithms based on PCA (Eigenface) and Fisher Linear Discriminant (FLD) feature decompositions.

This thesis explores two possible ways of detecting soft plaque present in the coronary arteries, using CTA imagery. The coronary arteries are vessels that supply oxidized blood to the cardiac muscle and are thus important for the proper functioning of heart. Cholesterol or reactive oxygen species from cigarette smoke and other toxins may get adhered to the walls of coronary arteries and trigger chronic inflammation that leads to formation of the soft plaque. When the soft plaque grows bigger in volume, it occludes the blood flow to the cardiac muscle and finally results in ischemic heart attack. Moreover, smaller plaque can easily rupture due to the blood flow in arteries and can result in complications such as stroke. Hence there is a need to detect the soft plaque using non-invasive or minimally invasive techniques. In CTA imagery, the cardiac muscle appears as a dark gray color, while the blood appears as dull white color and the the calcified plaque appears as bright white. The soft plaque has an intensity which falls between the intensity level of the blood and cardiac muscle, making it difficult to directly segment the soft plaque using standard segmentation methods. Soft plaque in its advanced stages forms a concavity in the blood lumen. A watershed based segmentation method was used to detect the presence of this concavity which in turn identifies the location of the soft plaque. For segmenting the soft plaque at its earlier stages, a novel segmentation technique was used. In this technique the surface is evolved based on a region-based energy calculated in the local neighborhood around each point on the evolving surface. This method seems to be superior to the watershed based segmentation method in detecting smaller plaque deposits.

La tesis se centra en la Visión por Computador y, más concretamente, en la segmentación de imágenes, la cual es una de las etapas básicas en el análisis de imágenes y consiste en la división de la imagen en un conjunto de regiones visualmente distintas y uniformes considerando su intensidad, color o textura.Se propone una estrategia basada en el uso complementario de la información de región y de frontera durante el proceso de segmentación, integración que permite paliar algunos de los problemas básicos de la segmentación tradicional. La información de frontera permite inicialmente identificar el número de regiones presentes en la imagen y colocar en el interior de cada una de ellas una semilla, con el objetivo de modelar estadísticamente las características de las regiones y definir de esta forma la información de región. Esta información, conjuntamente con la información de frontera, es utilizada en la definición de una función de energía que expresa las propiedades requeridas a la segmentación deseada: uniformidad en el interior de las regiones y contraste con las regiones vecinas en los límites. Un conjunto de regiones activas inician entonces su crecimiento, compitiendo por los píxeles de la imagen, con el objetivo de optimizar la función de energía o, en otras palabras, encontrar la segmentación que mejor se adecua a los requerimientos exprsados en dicha función. Finalmente, todo esta proceso ha sido considerado en una estructura piramidal, lo que nos permite refinar progresivamente el resultado de la segmentación y mejorar su coste computacional.La estrategia ha sido extendida al problema de segmentación de texturas, lo que implica algunas consideraciones básicas como el modelaje de las regiones a partir de un conjunto de características de textura y la extracción de la información de frontera cuando la textura es presente en la imagen.Finalmente, se ha llevado a cabo la extensión a la segmentación de imágenes teniendo en cuenta las propiedades de color y textura. En este sentido, el uso conjunto de técnicas no-paramétricas de estimación de la función de densidad para la descripción del color, y de características textuales basadas en la matriz de co-ocurrencia, ha sido propuesto para modelar adecuadamente y de forma completa las regiones de la imagen.La propuesta ha sido evaluada de forma objetiva y comparada con distintas técnicas de integración utilizando imágenes sintéticas. Además, se han incluido experimentos con imágenes reales con resultados muy positivos. / Image segmentation is an important research area in computer vision and many segmentation methods have been proposed. However, elemental segmentation techniques based on boundary or region approaches often fail to produce accurate segmentation results. Hence, in the last few years, there has been a tendency towards the integration of both techniques in order to improve the results by taking into account the complementary nature of such information. This thesis proposes a solution to the image segmentation integrating region and boundary information. Moreover, the method is extended to texture and colour texture segmentation.An exhaustive analysis of image segmentation techniques which integrate region and boundary information is carried out. Main strategies to perform the integration are identified and a classification of these approaches is proposed. Thus, the most relevant proposals are assorted and grouped in their corresponding approach. Moreover, characteristics of these strategies as well as the general lack of attention that is given to the texture is noted. The discussion of these aspects has been the origin of all the work evolved in this thesis, giving rise to two basic conclusions: first, the possibility of fusing several approaches to the integration of both information sources, and second, the necessity of a specific treatment for textured images.Next, an unsupervised segmentation strategy which integrates region and boundary information and incorporates three different approaches identified in the previous review is proposed. Specifically, the proposed image segmentation method combines the guidance of seed placement, the control of decision criterion and the boundary refinement approaches. The method is composed by two basic stages: initialisation and segmentation. Thus, in the first stage, the main contours of the image are used to identify the different regions present in the image and to adequately place a seed for each one in order to statistically model the region. Then, the segmentation stage is performed based on the active region model which allows us to take region and boundary information into account in order to segment the whole image. Specifically, regions start to shrink and expand guided by the optimisation of an energy function that ensures homogeneity properties inside regions and the presence of real edges at boundaries. Furthermore, with the aim of imitating the Human Vision System when a person is slowly approaching to a distant object, a pyramidal structure is considered. Hence, the method has been designed on a pyramidal representation which allows us to refine the region boundaries from a coarse to a fine resolution, and ensuring noise robustness as well as computation efficiency.The proposed segmentation strategy is then adapted to solve the problem of texture and colour texture segmentation. First, the proposed strategy is extended to texture segmentation which involves some considerations as the region modelling and the extraction of texture boundary information. Next, a method to integrate colour and textural properties is proposed, which is based on the use of texture descriptors and the estimation of colour behaviour by using non-parametric techniques of density estimation. Hence, the proposed strategy of segmentation is considered for the segmentation taking both colour and textural properties into account.Finally, the proposal of image segmentation strategy is objectively evaluated and then compared with some other relevant algorithms corresponding to the different strategies of region and boundary integration. Moreover, an evaluation of the segmentation results obtained on colour texture segmentation is performed. Furthermore, results on a wide set of real images are shown and discussed.

A forced landing for an Unmanned Aerial Vehicle (UAV) is required if there is an emergency on board that requires the aircraft to land immediately. Piloted aircraft in the same scenario have a human on board that is able to engage in the complex decision making process involved in the choice of a suitable landing location. If UAVs are to ever fly routinely in civilian airspace, then it is argued that the problem of finding a safe landing location for a forced landing is an important unresolved problem that must be addressed. This thesis presents the results of an investigation into the feasibility of using machine vision techniques to locate candidate landing sites for an autonomous UAV forced landing. The approach taken involves the segmentation of the image into areas that are large enough and free of obstacles; classification of the surface types of these areas; incorporating slope information from readily available digital terrain databases; and finally fusing these maps together using a high level set of simple linguistic fuzzy rules to create a final candidate landing site map. All techniques were evaluated on actual flight data collected from a Cessna 172 flying in South East Queensland. It was shown that the use of existing segmentation approaches from the literature did not provide the outputs required for this problem in the airborne images encountered in the gathered dataset. A simple method was then developed and tested that provided suitably sized landing areas that were free of obstacles and large enough to land. The advantage of this novel approach was that these areas could be extracted from the image directly without solving the difficult task of segmenting the entire image into the individual homogenous objects. A number of neural network classification approaches were tested with the surface types of candidate landing site regions extracted from the aerial images. A number of novel techniques were developed through experimentation with the classifiers that greatly improved upon the classification accuracy of the standard approaches considered. These novel techniques included: automatic generation of suitable output subclasses based on generic output classes of the classifier; an optimisation process for generating the best set of input features for the classifier based on an automated analysis of the feature space; the use of a multi-stage classification approach; and the generation of confidence measures based on the outputs of the neural network classifiers. The final classification result of the system performs significantly better than a human test pilot's classification interpretation of the dataset samples. In summary, the algorithms were able to locate candidate landing site areas that were free of obstacles 92.3 ±2.6% (99% confidence in the result) of the time, with free obstacle candidate landing site areas that were large enough to land in missed only 5.3 ±2.2% (99% confidence in the result) of the time. The neural network classification networks developed were able to classify the surface type of the candidate landing site areas to an accuracy of 93.9 ±3.7% (99% confidence in the result) for areas labelled as Very Certain. The overall surface type classification accuracy for the system (includes all candidate landing sites) was 91.95 ±4.2% (99% confidence in the result). These results were considered to be an excellent result as a human test pilot subject was only able to classify the same data set to an accuracy of 77.24 %. The thesis concludes that the techniques developed showed considerable promise and could be used immediately to enhance the safety of UAV operations. Recommendations include the testing of algorithms over a wider range of datasets and improvements to the surface type classification approach that incorporates contextual information in the image to further improve the classification accuracy.

[Truncated abstract] In this thesis, we introduce a mammogram analysis system developed for the automatic segmentation and analysis of mammograms. This original system has been designed to aid radiologists to detect breast cancer on mammograms. The system embodies attribute-driven segmentation in which the attributes of an image are extracted progressively in a step-by-step, hierarchical fashion. Global, low-level attributes obtained in the early stages are used to derive local, high-level attributes in later stages, leading to increasing refinement and accuracy in image segmentation and analysis. The proposed system can be characterized as: • a bootstrap engine driven by the attributes of the images; • a solid framework supporting the process of hierarchical segmentation; • a universal platform for the development and integration of segmentation and analysis techniques; and • an extensible database in which knowledge about the image is accumulated. Central to this system are three major components: 1. a series of applications for attribute acquisition; 2. a standard format for attribute normalization; and 3. a database for attribute storage and data exchange between applications. The first step of the automatic process is to segment the mammogram hierarchically into several distinctive regions that represent the anatomy of the breast. The adequacy and quality of the mammogram are then assessed using the anatomical features obtained from segmentation. Further image analysis, such as breast density classification and lesion detection, may then be carried out inside the breast region. Several domain-specific algorithms have therefore been developed for the attribute acquisition component in the system. These include: 1. automatic pectoral muscle segmentation; 2. adequacy assessment of positioning and exposure; and 3. contrast enhancement of mass lesions. An adaptive algorithm is described for automatic segmentation of the pectoral muscle on mammograms of mediolateral oblique (MLO) views

Submitted by Ronildo Prado (ronisp@ufscar.br) on 2017-08-22T14:32:30Z No. of bitstreams: 1 DissRCA.pdf: 1727058 bytes, checksum: 78d5444e767bf066e768b88a3a9ab535 (MD5) / Approved for entry into archive by Ronildo Prado (ronisp@ufscar.br) on 2017-08-22T14:32:38Z (GMT) No. of bitstreams: 1 DissRCA.pdf: 1727058 bytes, checksum: 78d5444e767bf066e768b88a3a9ab535 (MD5) / Approved for entry into archive by Ronildo Prado (ronisp@ufscar.br) on 2017-08-22T14:32:44Z (GMT) No. of bitstreams: 1 DissRCA.pdf: 1727058 bytes, checksum: 78d5444e767bf066e768b88a3a9ab535 (MD5) / Made available in DSpace on 2017-08-22T14:32:50Z (GMT). No. of bitstreams: 1 DissRCA.pdf: 1727058 bytes, checksum: 78d5444e767bf066e768b88a3a9ab535 (MD5) Previous issue date: 2017-06-02 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / We present the topics and theory of Mixture Models in a context of maximum likelihood and Bayesian inferece. We approach clustering methods in both contexts, with emphasis on the stochastic EM algorithm and the Dirichlet Process Mixture Model. We propose a new method, a modified stochastic EM algorithm, which can be used to estimate the parameters of a mixture model and the number of components. / Apresentamos o tópico e a teoria de Modelos de Mistura de Distribuições, revendo aspectos teóricos e interpretações de tais misturas. Desenvolvemos a teoria dos modelos nos contextos de máxima verossimilhança e de inferência bayesiana. Abordamos métodos de agrupamento já existentes em ambos os contextos, com ênfase em dois métodos, o algoritmo EM estocástico no contexto de máxima verossimilhança e o Modelo de Mistura com Processos de Dirichlet no contexto bayesiano. Propomos um novo método, uma modificação do algoritmo EM Estocástico, que pode ser utilizado para estimar os parâmetros de uma mistura de componentes enquanto permite soluções com número distinto de grupos.

Made available in DSpace on 2014-12-17T15:48:12Z (GMT). No. of bitstreams: 1 LucasMO.pdf: 1455032 bytes, checksum: 6bc4218b3d779cfc9915c6a2efda34f1 (MD5) Previous issue date: 2007-02-23 / Conselho Nacional de Desenvolvimento Cient?fico e Tecnol?gico / Image segmentation is the process of subdiving an image into constituent regions or objects that have similar features. In video segmentation, more than subdividing the frames in object that have similar features, there is a consistency requirement among segmentations of successive frames of the video. Fuzzy segmentation is a region growing technique that assigns to each element in an image (which may have been corrupted by noise and/or shading) a grade of membership between 0 and 1 to an object. In this work we present an application that uses a fuzzy segmentation algorithm to identify and select particles in micrographs and an extension of the algorithm to perform video segmentation. Here, we treat a video shot is treated as a three-dimensional volume with different z slices being occupied by different frames of the video shot. The volume is interactively segmented based on selected seed elements, that will determine the af&#64257;nity functions based on their motion and color properties. The color information can be extracted from a speci&#64257;c color space or from three channels of a set of color models that are selected based on the correlation of the information from all channels. The motion information is provided into the form of dense optical &#64258;ows maps. Finally, segmentation of real and synthetic videos and their application in a non-photorealistic rendering (NPR) toll are presented / Segmenta??o de imagens ? o processo que subdivide uma imagem em partes ou objetos de acordo com alguma caracter?stica comum. J? na segmenta??o de v?deos, al?m dos quadros serem divididos em fun??o de alguma caracter?stica, ? necess?rio obter uma coer?ncia temporal entre as segmenta??es de frames sucessivos do v?deo. A segmenta??o fuzzy ? uma t?cnica de segmenta??o por crescimento de regi?es que determina para cada elemento da imagem um grau de pertin?ncia (entre zero e um) indicando a con&#64257;an?a de que esse elemento perten?a a um determinado objeto ou regi?o existente na imagem. O presente trabalho apresenta uma aplica??o do algoritmo de segmenta??o fuzzy de imagem, e a extens?o deste para segmentar v?deos coloridos. Nesse contexto, os v?deos s?o tratados como volumes 3D e o crescimento das regi?es ? realizado usando fun??es de a&#64257;nidade que atribuem a cada pixel um valor entre zero e um para indicar o grau de pertin?ncia que esse pixel tem com os objetos segmentados. Para segmentar as seq??ncias foram utilizadas informa??es de movimento e de cor, sendo que essa ?ltima ? proveniente de um modelo de cor convencional, ou atrav?s de uma metodologia que utiliza a correla??o de Pearson para selecionar os melhores canais para realizar a segmenta??o. A informa??o de movimento foi extra?da atrav?s do c?lculo do &#64258;uxo ?ptico entre dois frames adjacentes. Por ?ltimo ? apresentada uma an?lise do comportamento do algoritmo na segmenta??o de seis v?deos e um exemplo de uma aplica??o que utiliza os mapas de segmenta??o para realizar renderiza??es que n?o sejam foto real?sticas

Les contours actifs sont parmi les méthodes de segmentation d'images les plus utilisées et de nombreuses implémentations ont vu le jour durant ces 25 dernières années. Parmi elles, l'approche greedy est considérée comme l'une des plus rapides et des plus stables. Toutefois, quelle que soit l'implémentation choisie, les résultats de segmentation souffrent grandement en présence d'occlusions, de concavités ou de déformation anormales de la forme. Si l'on dispose d'informations a priori sur la forme recherchée, alors son incorporation à un modèle existant peut permettre d'améliorer très nettement les résultats de segmentation. Dans cette thèse, l'inclusion de ce type de contraintes de formes dans un modèle de contour actif explicite est proposée. Afin de garantir une invariance à la rotation, à la translation et au changement d'échelle, les descripteurs de Fourier sont utilisés. Contrairement à la plupart des méthodes existantes, qui comparent la forme de référence et le contour actif en cours d'évolution dans le domaine d'origine par le biais d'une transformation inverse, la méthode proposée ici réalise cette comparaison dans l'espace des descripteurs. Cela assure à notre approche un faible temps de calcul et lui permet d'être indépendante du nombre de points de contrôle choisis pour le contour actif. En revanche, cela induit un biais dans la phase des coefficients de Fourier, handicapant l'invariance à la rotation. Ce problème est résolu par un algorithme original. Les expérimentations indiquent clairement que l'utilisation de ce type de contrainte de forme améliore significativement les résultats de segmentation du modèle de contour actif utilisé. / Active contours are widely used for image segmentation. There are many implementations of active contours. The greedy algorithm is being regarded as one of the fastest and stable implementations. No matter which implementation is being employed, the segmentation results suffer greatly in the presence of occlusion, context noise, concavities or abnormal deformation of shape. If some prior knowledge about the shape of the object is available, then its addition to an existing model can greatly improve the segmentation results. In this thesis inclusion of such shape constraints for explicit active contours is being implemented. These shape priors are introduced through the use of robust Fourier based descriptors which makes them invariant to the translation, scaling and rotation factors and enables the deformable model to converge towards the prior shape even in the presence of occlusion and contextual noise. Unlike most existing methods which compare the reference shape and evolving contour in the spatial domain by applying the inverse transforms, our proposed method realizes such comparisons entirely in the descriptor space. This not only decreases the computational time but also allows our method to be independent of the number of control points chosen for the description of the active contour. This formulation however, may introduce certain anomalies in the phase of the descriptors which affects the rotation invariance. This problem has been solved by an original algorithm. Experimental results clearly indicate that the inclusion of these shape priors significantly improved the segmentation results of the active contour model being used.

[pt] A Segmentação de imagens representa uma etapa fundamental na análise de imagens e geralmente envolve um alto custo computacional, especialmente ao lidar com grandes volumes de dados. Devido ao significativo aumento nas resoluções espaciais, espectrais e temporais das imagens de sensoriamento remoto nos últimos anos, as soluções sequenciais e paralelas atualmente empregadas não conseguem alcançar os níveis de desempenho e escalabilidade esperados. Este trabalho propõe um método de segmentação de imagens distribuída capaz de lidar, de forma escalável e eficiente, com imagens grandes de altíssima resolução. A solução proposta é baseada no modelo MapReduce, que oferece uma estrutura altamente escalável e confiável para armazenar e processar dados muito grandes em ambientes de computação em clusters e, em particular, também para nuvens privadas e comerciais. O método proposto é extensível a qualquer algoritmo de crescimento de regiões podendo também ser adaptado para outros modelos. A solução foi implementada e validada usando a plataforma Hadoop. Os resultados experimentais comprovam a viabilidade de realizar a segmentação distribuída sobre o modelo MapReduce por intermédio da computação na nuvem. / [en] Image segmentation is a critical step in image analysis, and generally involves a high computational cost, especially when dealing with large volumes of data. Given the significant increase in the spatial, spectral and temporal resolutions of remote sensing imagery in the last years, current sequential and parallel solutions fail to deliver the expected performance and scalability. This work proposes a distributed image segmentation method, capable of handling very large high-resolution images in an efficient and scalable way. The proposed solution is based on the MapReduce model, which offers a highly scalable and reliable framework for storing and processing massive data in cluster environments and in private and public computing clouds. The proposed method is extendable to any region-growing algorithm and can be adapted to other models. The solution was implemented and validated using the Hadoop platform. Experimental results attest the viability of performing distributed segmentation over the MapReduce model through cloud computing.