Registration of a group of images generally only gives a pointwise, dense correspondence defined over the whole image plane or volume, without having any specific description of any common structure that exists in every image. Furthermore, identifying tissue classes and structures that are significant across the group is often required for analysis, as well as the correspondence. The overall aim is instead to perform registration, segmentation, and modelling simultaneously, so that the registration can assist the segmentation, and vice versa. However, structural information does play a role in conventional registration, in that if the registration is successful, it would be expected structures to be aligned to some extent. Hence, we perform initial experiments to investigate whether there is explicit structural information present in the shape of the registration objective function about the optimum. We perturbed one image locally with a diffeomorphism, and found interesting structure in the shape of the quality of fit function. Then, we proceed to add explicit structural information into registration framework, using various types of structural information derived from the original intensity images. For the case of MR brain images, we augment each intensity image with its own set of tissue fraction images, plus intensity gradient images, which form an image ensemble for each example. Then, we perform groupwise registration by using these ensembles of images. We apply the method to four different real-world datasets, for which ground-truth annotation is available. It is shown that the method can give a greater than 25% improvement on the three difficult datasets, when compared to using intensity-based registration alone. On the easier dataset, it improves upon intensity-based registration, and achieves results comparable with the previous method.

yes / This paper presents a methodology for fault detection, fault prediction and fault isolation based on the integration of hidden Markov modelling (HMM) and Bayesian networks (BN). This addresses the nonlinear and non-Gaussian data characteristics to support fault detection and prediction, within an explainable hybrid framework that captures causality in the complex engineered system. The proposed methodology is based on the analysis of the pattern of similarity in the log-likelihood (LL) sequences against the training data for the mixture of Gaussians HMM (MoG-HMM). The BN model identifies the root cause of detected/predicted faults, using the information propagated from the HMM model as empirical evidence. The feasibility and effectiveness of the presented approach are discussed in conjunction with the application to a real-world case study of an automotive exhaust gas Aftertreatment system. The paper details the implementation of the methodology to this case study, with data available from real-world usage of the system. The results show that the proposed methodology identifies the fault faster and attributes the fault to the correct root cause. While the proposed methodology is illustrated with an automotive case study, its applicability is much wider to the fault detection and prediction problem of any similar complex engineered system.

Este trabalho mostra que a suavização Gaussiana pode exercer outra função além da filtração. Considerando-se imagens binárias, este processo pode funcionar como uma espécie de marcador, que modifica as feições das fronteiras entre duas regiões homogêneas contrastantes. Tais feições são pontos de concavidades, de convexidades ou de bordas em linha reta. Ou seja, toda a informação necessária para se caracterizar a forma bidimensional de uma região. A quantidade de suavização realizada em cada ponto depende da configuração preto/branco que compõe a vizinhança onde este se situa. Isto significa que cada ponto sofre uma quantidade particular de modificação, a qual reflete a interface local entre o objeto e o fundo. Então, para detectar tais feições, basta quantificar a suavização em cada ponto. No entanto, a discriminação pixel a pixel exige que a distribuição Gaussiana apresente boa localização, o que só acontece em escalas muito baixas (σ≅0,5). Assim, propõe-se uma distribuição construída a partir da soma de duas Gaussianas. Uma é bem estreita para garantir a boa localização e a outra possui abertura irrestrita para representar a escala desejada. Para confirmar a propriedade de marcação dessa distribuição, são propostos três detectores de corners de contorno, os quais são aplicados à detecção de pontos dominantes. O primeiro utiliza a entropia de Shannon para quantificar a suavização em cada ponto. O segundo utiliza as probabilidades de objeto e de fundo contidos na vizinhança observada. O terceiro utiliza a diferença entre Gaussianas (DoG) para determinar a quantidade suavizada, porém com a restrição de que uma das versões da imagem tenha suavização desprezível, para garantir a boa localização. Este trabalho se fundamenta na física da luz e na visão biológica. Os ótimos resultados apresentados sugerem que a detecção de curvaturas do sistema visual pode ocorrer na retina. / This work shows that the Gaussian smoothing can have additional function to filtration. Considering the binary images, this process can operate as a kind of marker that changes the features of the boundaries between two contrasting homogeneous regions. These features are points of concavities, convexities or straight edges, which are all the necessary information to characterize the two-dimensional shape of a region. The amount of smoothing performed at each point depends on the black/white configuration that composes the neighborhood where the point is located. This means that each point suffers a particular modification, which reflects the local interface between object and background. Thus, to detect such features, one must quantify the smoothing at each point. However, pixel-wise discrimination requires that the Gaussian distribution does not suffer flattening, which occurs in very low scales (σ≅0.5), only. Thus, it is proposed a distribution built from the sum of two Gaussians. One must be very narrow to ensure good localization, and the other is free to represent the desired scale. To confirm the property of marking, three boundary based corner detectors are proposed, which are applied to the detection of dominant points. The first uses the Shannon\'s entropy to quantify the smoothing at each point. The second uses the probabilities of object and background contained in the local neighborhood. The third uses the difference of Gaussians (DoG) to determine the amount of smoothing. This Work relies on the physics of light and biological vision. The presented results are good enough to suggest that the curvature detection, in visual system, occurs in the retina.

Este trabalho mostra que a suavização Gaussiana pode exercer outra função além da filtração. Considerando-se imagens binárias, este processo pode funcionar como uma espécie de marcador, que modifica as feições das fronteiras entre duas regiões homogêneas contrastantes. Tais feições são pontos de concavidades, de convexidades ou de bordas em linha reta. Ou seja, toda a informação necessária para se caracterizar a forma bidimensional de uma região. A quantidade de suavização realizada em cada ponto depende da configuração preto/branco que compõe a vizinhança onde este se situa. Isto significa que cada ponto sofre uma quantidade particular de modificação, a qual reflete a interface local entre o objeto e o fundo. Então, para detectar tais feições, basta quantificar a suavização em cada ponto. No entanto, a discriminação pixel a pixel exige que a distribuição Gaussiana apresente boa localização, o que só acontece em escalas muito baixas (σ≅0,5). Assim, propõe-se uma distribuição construída a partir da soma de duas Gaussianas. Uma é bem estreita para garantir a boa localização e a outra possui abertura irrestrita para representar a escala desejada. Para confirmar a propriedade de marcação dessa distribuição, são propostos três detectores de corners de contorno, os quais são aplicados à detecção de pontos dominantes. O primeiro utiliza a entropia de Shannon para quantificar a suavização em cada ponto. O segundo utiliza as probabilidades de objeto e de fundo contidos na vizinhança observada. O terceiro utiliza a diferença entre Gaussianas (DoG) para determinar a quantidade suavizada, porém com a restrição de que uma das versões da imagem tenha suavização desprezível, para garantir a boa localização. Este trabalho se fundamenta na física da luz e na visão biológica. Os ótimos resultados apresentados sugerem que a detecção de curvaturas do sistema visual pode ocorrer na retina. / This work shows that the Gaussian smoothing can have additional function to filtration. Considering the binary images, this process can operate as a kind of marker that changes the features of the boundaries between two contrasting homogeneous regions. These features are points of concavities, convexities or straight edges, which are all the necessary information to characterize the two-dimensional shape of a region. The amount of smoothing performed at each point depends on the black/white configuration that composes the neighborhood where the point is located. This means that each point suffers a particular modification, which reflects the local interface between object and background. Thus, to detect such features, one must quantify the smoothing at each point. However, pixel-wise discrimination requires that the Gaussian distribution does not suffer flattening, which occurs in very low scales (σ≅0.5), only. Thus, it is proposed a distribution built from the sum of two Gaussians. One must be very narrow to ensure good localization, and the other is free to represent the desired scale. To confirm the property of marking, three boundary based corner detectors are proposed, which are applied to the detection of dominant points. The first uses the Shannon\'s entropy to quantify the smoothing at each point. The second uses the probabilities of object and background contained in the local neighborhood. The third uses the difference of Gaussians (DoG) to determine the amount of smoothing. This Work relies on the physics of light and biological vision. The presented results are good enough to suggest that the curvature detection, in visual system, occurs in the retina.

A COMPARATIVE EVALUATION OF FOREGROUND / BACKGROUND SEGMENTATION ALGORITHMS Pakyurek, Muhammet M.Sc., Department of Electrical and Electronics Engineering Supervisor: Prof. Dr. G&ouml / zde Bozdagi Akar September 2012, 77 pages Foreground Background segmentation is a process which separates the stationary objects from the moving objects on the scene. It plays significant role in computer vision applications. In this study, several background foreground segmentation algorithms are analyzed by changing their critical parameters individually to see the sensitivity of the algorithms to some difficulties in background segmentation applications. These difficulties are illumination level, view angles of camera, noise level, and range of the objects. This study is mainly comprised of two parts. In the first part, some well-known algorithms based on pixel difference, probability, and codebook are explained and implemented by providing implementation details. The second part includes the evaluation of the performances of the algorithms which is based on the comparison v between the foreground background regions indicated by the algorithms and ground truth. Therefore, some metrics including precision, recall and f-measures are defined at first. Then, the data set videos having different scenarios are run for each algorithm to compare the performances. Finally, the performances of each algorithm along with optimal values of their parameters are given based on f measure.

This thesis presents a new technique for performing image analysis, synthesis, and modification using a generalized Gaussian model. The joint time-frequency characteristics of a generalized Gaussian are combined with the flexibility of the analysis-by-synthesis (ABS) decomposition technique to form the basis of the model. The good localization properties of the Gaussian make it an appealing basis function for image analysis, while the ABS process provides a more flexible representation with enhanced functionality. ABS was first explored in conjunction with sinusoidal modeling of speech and audio signals [George87]. A 2D extension of the ABS technique is developed here to perform the image decomposition. This model forms the basis for new approaches in image analysis and enhancement. The major contribution is made in the resolution enhancement of images generated using coherent imaging modalities such as Synthetic Aperture Radar (SAR) and ultrasound. The ABS generalized Gaussian model is used to decouple natural image features from the speckle and facilitate independent control over feature characteristics and speckle granularity. This has the beneficial effect of increasing the perceived resolution and reducing the obtrusiveness of the speckle while preserving the edges and the definition of the image features. A consequence of its inherent flexibility, the model does not preclude image processing applications for non-coherent image data. This is illustrated by its application as a feature extraction tool for a FLIR imagery complexity measure.

Correspondance de forme est un problème fondamental dans de nombreuses disciplines de recherche, tels que la géométrie algorithmique, vision par ordinateur et l'infographie. Communément définie comme un problème de trouver injective/ multivaluée correspondance entre une source et une cible, il constitue une tâche centrale dans de nombreuses applications y compris le transfert de attributes, récupération des formes etc. Dans récupération des formes, on peut d'abord calculer la correspondance entre la forme de requête et les formes dans une base de données, puis obtenir le meilleure correspondance en utilisant une mesure de qualité de correspondance prédéfini. Il est également particulièrement avantageuse dans les applications basées sur la modélisation statistique des formes. En encapsulant les propriétés statistiques de l'anatomie du sujet dans le model de forme, comme variations géométriques, des variations de densité, etc., il est utile non seulement pour l'analyse des structures anatomiques telles que des organes ou des os et leur variations valides, mais aussi pour apprendre les modèle de déformation de la classe d'objets. Dans cette thèse, nous nous intéressons à une enquête sur une nouvelle méthode d'appariement de forme qui exploite grande redondance de l'information à partir des ensembles de données dynamiques, variables dans le temps. Récemment, une grande quantité de recherches ont été effectuées en infographie sur l'établissement de correspondances entre les mailles statiques (Anguelov, Srinivasan et al. 2005, Aiger, Mitra et al. 2008, Castellani, Cristani et al. 2008). Ces méthodes reposent sur les caractéristiques géométriques ou les propriétés extrinsèques/intrinsèques des surfaces statiques (Lipman et Funkhouser 2009, Sun, Ovsjanikov et al. 2009, Ovsjanikov, Mérigot et al. 2010, Kim, Lipman et al., 2011) pour élaguer efficacement les paires. Bien que l'utilisation de la caractéristique géométrique est encore un standard d'or, les méthodes reposant uniquement sur l'information statique de formes peuvent générer dans les résultats de correspondance grossièrement trompeurs lorsque les formes sont radicalement différentes ou ne contiennent pas suffisamment de caractéristiques géométriques. [...] / 3D geometry modelling tools and 3D scanners become more enhanced and to a greater degree affordable today. Thus, development of the new algorithms in geometry processing, shape analysis and shape correspondence gather momentum in computer graphics. Those algorithms steadily extend and increasingly replace prevailing methods based on images and videos. Non-rigid shape correspondence or deformable shape matching has been a long-studied subject in computer graphics and related research fields. Not to forget, shape correspondence is of wide use in many applications such as statistical shape analysis, motion cloning, texture transfer, medical applications and many more. However, robust and efficient non-rigid shape correspondence still remains a challenging task due to fundamental variations between individual subjects, acquisition noise and the number of degrees of freedom involved in correspondence search. Although dynamic 2D/3D intra-subject shape correspondence problem has been addressed in the rich set of previous methods, dynamic inter-subject shape correspondence received much less attention. The primary purpose of our research is to develop a novel, efficient, robust deforming shape analysis and correspondence framework for animated meshes based on their dynamic and motion properties. We elaborate our method by exploiting a profitable set of motion data exhibited by deforming meshes with time-varying embedding. Our approach is based on an observation that a dynamic, deforming shape of a given subject contains much more information rather than a single static posture of it. That is different from the existing methods that rely on static shape information for shape correspondence and analysis.Our framework of deforming shape analysis and correspondence of animated meshes is comprised of several major contributions: a new dynamic feature detection technique based on multi-scale animated mesh’s deformation characteristics, novel dynamic feature descriptor, and an adaptation of a robust graph-based feature correspondence approach followed by the fine matching of the animated meshes. [...]

Cette thèse présente des travaux de modélisation mathématique de la croissance tumorale. On détaille dans ce manuscrit la construction d’indicateurs de bio-imagerie, destinés à quantifier l’hétérogénéité tumorale. Un modèle d’équations aux dérivées partielles constitué de deux types de cellules tumorales est étudié par la suite. Le paramétrage de ce modèle est propre à chaque patient et à chaque lésion. Il est effectué grâce à des données d’imagerie médicale (IRM ou scanner), ce qui constitue une méthode non invasive pour le patient. Les indicateurs ainsi que le modèle décrit ont été utilisés dans le cadre du suivi des métastases des lésions rénales de 5 patients traités avec un médicament anti-angiogénique. Enfin, la dernière partie a pour objectif de distinguer différents types de lésions rénales (malignes ou non) grâce à l’imagerie afin de limiter les chirurgies inutiles. On s’est particulièrement attaché à distinguer les carcinomes rénaux à cellules claires des angiomyolipomes pauvres en graisse. / This document deals with mathematical modelling of tumour growth. Biological indicators based on medical images are constructed in order to quantify tumoral heterogeneity. In the first part, a partial differential equations model made of two distinct cell subtypes is being studied. The model’s parameters are unique for each patient and each lesion. They are computed thanks to medical images (MRI or scan), which is a non-invasive method for the patient. Both the indicators and the model described are used on the cases of 5 patients treated with an anti-angiogenic medicine. The last part of the document aims at distinguishing different renal tumour subtypes that can be malignant or benign. Angiomyolipomas and renal cells carcinomas were particulary studied in the last part of the document.