This thesis deals with a graph cut approach for segmentation of the anatomical structures in volumetric medical images. The method used requires some voxels to be a priori identified as object or background seeds. The goal of this thesis is implementation of the graph cut method and construction of an interactive tool for segmentation. Selected metod's behaviour is examined on two datasets with manually-guided segmentation results. Testing is in one case focused on the influence of method parameters on segmentation results, while in the other deals with method tolerance towards various signal-to-noise and contrast-to-noise ratios on input. To assess the consistency of a given segmentation with the ground-truth the F-measure is used.

This thesis investigates two well defined problems in image segmentation, viz. interactive and semantic image segmentation. Interactive segmentation involves power assisting a user in cutting out objects from an image, whereas semantic segmentation involves partitioning pixels in an image into object categories. We investigate various models and energy formulations for both these problems in this thesis. In order to improve the performance of interactive systems, low level texture features are introduced as a replacement for the more commonly used RGB features. To quantify the improvement obtained by using these texture features, two annotated datasets of images are introduced (one consisting of natural images, and the other consisting of camouflaged objects). A significant improvement in performance is observed when using texture features for the case of monochrome images and images containing camouflaged objects. We also explore adding mid-level cues such as shape constraints into interactive segmentation by introducing the idea of geodesic star convexity, which extends the existing notion of a star convexity prior in two important ways: (i) It allows for multiple star centres as opposed to single stars in the original prior and (ii) It generalises the shape constraint by allowing for Geodesic paths as opposed to Euclidean rays. Global minima of our energy function can be obtained subject to these new constraints. We also introduce Geodesic Forests, which exploit the structure of shortest paths in implementing the extended constraints. These extensions to star convexity allow us to use such constraints in a practical segmentation system. This system is evaluated by means of a “robot user” to measure the amount of interaction required in a precise way, and it is shown that having shape constraints reduces user effort significantly compared to existing interactive systems. We also introduce a new and harder dataset which augments the existing GrabCut dataset with more realistic images and ground truth taken from the PASCAL VOC segmentation challenge. In the latter part of the thesis, we bring in object category level information in order to make the interactive segmentation tasks easier, and move towards fully automated semantic segmentation. An algorithm to automatically segment humans from cluttered images given their bounding boxes is presented. A top down segmentation of the human is obtained using classifiers trained to predict segmentation masks from local HOG descriptors. These masks are then combined with bottom up image information in a local GrabCut like procedure. This algorithm is later completely automated to segment humans without requiring a bounding box, and is quantitatively compared with other semantic segmentation methods. We also introduce a novel way to acquire large quantities of segmented training data relatively effortlessly using the Kinect. In the final part of this work, we explore various semantic segmentation methods based on learning using bottom up super-pixelisations. Different methods of combining multiple super-pixelisations are discussed and quantitatively evaluated on two segmentation datasets. We observe that simple combinations of independently trained classifiers on single super-pixelisations perform almost as good as complex methods based on jointly learning across multiple super-pixelisations. We also explore CRF based formulations for semantic segmentation, and introduce novel visual words based object boundary description in the energy formulation. The object appearance and boundary parameters are trained jointly using structured output learning methods, and the benefit of adding pairwise terms is quantified on two different datasets.

A feature of minimizing images of a class of binary Markov random field energies is introduced and proved. Using this, the collection of minimizing images of levels of higher order, levelable MRF energies is shown to be a monotone collection. This implies that these images can be combined to give minimizing images of the MRF energy itself. Due to the recent developments, second and third order binary MRF energies of the mentioned class are known to be exactly minimized by maximum flow/minimum cut computations on appropriately constructed graphs. With the aid of these developments an exact and efficient algorithm to minimize levelable second and third order MRF energies, which is composed of a series of maximum flow/minimum cut computations, is proposed and applications of the proposed algorithm to image restoration are given.

We develop a generic Graph Cut-based semiautomatic multiobject image segmentation method principally for use in routine medical applications ranging from tasks involving few objects in 2D images to fairly complex near whole-body 3D image segmentation. The flexible formulation of the method allows its straightforward adaption to a given application.\linebreak In particular, the graph-based vicinity prior model we propose, defined as shortest-path pairwise constraints on the object adjacency graph, can be easily reformulated to account for the spatial relationships between objects in a given problem instance. The segmentation algorithm can be tailored to the runtime requirements of the application and the online storage capacities of the computing platform by an efficient and controllable Voronoi tessellation clustering of the input image which achieves a good balance between cluster compactness and boundary adherence criteria. Qualitative and quantitative comprehensive evaluation and comparison with the standard Potts model confirm that the vicinity prior model brings significant improvements in the correct segmentation of distinct objects of identical intensity, the accurate placement of object boundaries and the robustness of segmentation with respect to clustering resolution. Comparative evaluation of the clustering method with competing ones confirms its benefits in terms of runtime and quality of produced partitions. Importantly, compared to voxel segmentation, the clustering step improves both overall runtime and memory footprint of the segmentation process up to an order of magnitude virtually without compromising the segmentation quality.

L'objectif de cette thèse est de faciliter le diagnostic du cancer de la vessie. Durant une cystoscopie, un endoscope est introduit dans la vessie pour explorer la paroi interne de l'organe qui est visualisée sur un écran. Cependant, le faible champ de vue de l'instrument complique le diagnostic et le suivi des lésions. Cette thèse présente des algorithmes pour la création de cartes bi- et tridimensionnelles à large champ de vue à partir de vidéo-séquences cystoscopiques. En utilisant les avancées récentes dans le domaine de la minimisation d'énergies discrètes, nous proposons des fonctions coût indépendantes des transformations géométriques requises pour recaler de façon robuste et précise des paires d'images avec un faible recouvrement spatial. Ces transformations sont requises pour construire des cartes lorsque des trajectoires d'images se croisent ou se superposent. Nos algorithmes détectent automatiquement de telles trajectoires et réalisent une correction globale de la position des images dans la carte. Finalement, un algorithme de minimisation d'énergie compense les faibles discontinuités de textures restantes et atténue les fortes variations d'illuminations de la scène. Ainsi, les cartes texturées sont uniquement construites avec les meilleures informations (couleurs et textures) pouvant être extraites des données redondantes des vidéo-séquences. Les algorithmes sont évalués quantitativement et qualitativement avec des fantômes réalistes et des données cliniques. Ces tests mettent en lumière la robustesse et la précision de nos algorithmes. La cohérence visuelle des cartes obtenues dépassent celles des méthodes de cartographie de la vessie de la littérature / The aim of this thesis is to facilitate bladder cancer diagnosis. The reference clinical examination is cystoscopy, where an endoscope, inserted into the bladder, allows to visually explore the organ's internal walls on a monitor. The main restriction is the small field of view (FOV) of the instrument, which complicates lesion diagnosis, follow-up and treatment traceability.In this thesis, we propose robust and accurate algorithms to create two- and three-dimensional large FOV maps from cystoscopic video-sequences. Based on recent advances in the field of discrete energy minimization, we propose transformation-invariant cost functions, which allow to robustly register image pairs, related by large viewpoint changes, with sub-pixel accuracy. The transformations linking such image pairs, which current state-of-the-art bladder image registration techniques are unable to robustly estimate, are required to construct maps with several overlapping image trajectories. We detect such overlapping trajectories automatically and perform non-linear global map correction. Finally, the proposed energy minimization based map compositing algorithm compensates small texture misalignments and attenuates strong exposure differences. The obtained textured maps are composed by a maximum of information/quality available from the redundant data of the video-sequence. We evaluate the proposed methods both quantitatively and qualitatively on realistic phantom and clinical data sets. The results demonstrate the robustness of the algorithms, and the obtained maps outperform state-of-the-art approaches in registration accuracy and global map coherence

Vários métodos tradicionais de segmentação de imagens, como a transformada de watershed de marcado- res e métodos de conexidade fuzzy (Relative Fuzzy Connectedness- RFC, Iterative Relative Fuzzy Connected- ness - IRFC), podem ser implementados de modo eficiente utilizando o método em grafos da Transformada Imagem-Floresta (Image Foresting Transform - IFT). No entanto, a carência de termos de regularização de fronteira em sua formulação fazem com que a borda do objeto segmentado possa ser altamente irregular. Um modo de contornar isto é por meio do uso de restrições de forma do objeto, que favoreçam formas mais regulares, como na recente restrição de convexidade geodésica em estrela (Geodesic Star Convexity - GSC). Neste trabalho, apresentamos uma nova restrição de forma, chamada de Faixa de Restrição Geodésica (Geodesic Band Constraint - GBC), que pode ser incorporada eficientemente em uma sub-classe do fra- mework de corte em grafos generalizado (Generalized Graph Cut - GGC), que inclui métodos pela IFT. É apresentada uma prova da otimalidade do novo algoritmo em termos de um mínimo global de uma função de energia sujeita às novas restrições de borda. A faixa de restrição geodésica nos ajuda a regularizar a borda dos objetos, consequentemente melhorando a segmentação de objetos com formas mais regulares, mantendo o baixo custo computacional da IFT. A GBC pode também ser usada conjuntamente com um mapa de custos pré estabelecido, baseado em um modelo de forma, de modo a direcionar a segmentação a seguir uma dada forma desejada, com grau de liberdade de escala e demais deformações controladas por um parâmetro único. Essa nova restrição também pode ser combinada com a GSC e com as restrições de polaridade de borda sem custo adicional. O método é demonstrado em imagens naturais, sintéticas e médicas, sendo estas provenientes de tomografias computadorizadas e de ressonância magnética. / In this work, we present a novel boundary constraint, which we denote as the Geodesic Band Constraint (GBC), and we show how it can be efficiently incorporated into a subclass of the Generalized Graph Cut framework (GGC). We include a proof of the optimality of the new algorithm in terms of a global minimum of an energy function subject to the new boundary constraints. The Geodesic Band Constraint helps regularizing the boundary, and consequently, improves the segmentation of objects with more regular shape, while keeping the low computational costs of the Image Foresting Transform (IFT). It can also be combined with the Geodesic Star Convexity prior, and with polarity constraints, at no additional cost.

<p>Many different approaches have been taken towards solving the stereo correspondence problem and great progress has been made within the field during the last decade. This is mainly thanks to newly evolved global optimization techniques and better ways to compute pixel dissimilarity between views. The most successful algorithms are based on approaches that explicitly model smoothness assumptions made about the physical world, with image segmentation and plane fitting being two frequently used techniques.</p><p>Within the project, a survey of state of the art stereo algorithms was conducted and the theory behind them is explained. Techniques found interesting were implemented for experimental trials and an algorithm aiming to achieve state of the art performance was implemented and evaluated. For several cases, state of the art performance was reached.</p><p>To keep down the computational complexity, an algorithm relying on local winner-take-all optimization, image segmentation and plane fitting was compared against minimizing a global energy function formulated on pixel level. Experiments show that the local approach in several cases can match the global approach, but that problems sometimes arise – especially when large areas that lack texture are present. Such problematic areas are better handled by the explicit modeling of smoothness in global energy minimization.</p><p>Lastly, disparity estimation for image sequences was explored and some ideas on how to use temporal information were implemented and tried. The ideas mainly relied on motion detection to determine parts that are static in a sequence of frames. Stereo correspondence for sequences is a rather new research field, and there is still a lot of work to be made.</p>

Vários métodos tradicionais de segmentação de imagens, como a transformada de watershed de marcado- res e métodos de conexidade fuzzy (Relative Fuzzy Connectedness- RFC, Iterative Relative Fuzzy Connected- ness - IRFC), podem ser implementados de modo eficiente utilizando o método em grafos da Transformada Imagem-Floresta (Image Foresting Transform - IFT). No entanto, a carência de termos de regularização de fronteira em sua formulação fazem com que a borda do objeto segmentado possa ser altamente irregular. Um modo de contornar isto é por meio do uso de restrições de forma do objeto, que favoreçam formas mais regulares, como na recente restrição de convexidade geodésica em estrela (Geodesic Star Convexity - GSC). Neste trabalho, apresentamos uma nova restrição de forma, chamada de Faixa de Restrição Geodésica (Geodesic Band Constraint - GBC), que pode ser incorporada eficientemente em uma sub-classe do fra- mework de corte em grafos generalizado (Generalized Graph Cut - GGC), que inclui métodos pela IFT. É apresentada uma prova da otimalidade do novo algoritmo em termos de um mínimo global de uma função de energia sujeita às novas restrições de borda. A faixa de restrição geodésica nos ajuda a regularizar a borda dos objetos, consequentemente melhorando a segmentação de objetos com formas mais regulares, mantendo o baixo custo computacional da IFT. A GBC pode também ser usada conjuntamente com um mapa de custos pré estabelecido, baseado em um modelo de forma, de modo a direcionar a segmentação a seguir uma dada forma desejada, com grau de liberdade de escala e demais deformações controladas por um parâmetro único. Essa nova restrição também pode ser combinada com a GSC e com as restrições de polaridade de borda sem custo adicional. O método é demonstrado em imagens naturais, sintéticas e médicas, sendo estas provenientes de tomografias computadorizadas e de ressonância magnética. / In this work, we present a novel boundary constraint, which we denote as the Geodesic Band Constraint (GBC), and we show how it can be efficiently incorporated into a subclass of the Generalized Graph Cut framework (GGC). We include a proof of the optimality of the new algorithm in terms of a global minimum of an energy function subject to the new boundary constraints. The Geodesic Band Constraint helps regularizing the boundary, and consequently, improves the segmentation of objects with more regular shape, while keeping the low computational costs of the Image Foresting Transform (IFT). It can also be combined with the Geodesic Star Convexity prior, and with polarity constraints, at no additional cost.

This thesis deals with issues automatic composing panoramic photos from individual photos. Gradually examines the various steps of algorithms and methods used in them, which are used in creating panoramas. It also focuses on the design of the own system based on methods discussed to construct panoramas. This system is implemented using OpenCV library and it is created also a graphical interface using a Qt library. Finally, are in this thesis evaluated outcomes of this designed and implemented system on available datasets.

Ce travail de thèse concerne l'analyse structurelle des maillages triangulaires surfaciques, ainsi que leur traitement en vue de l'amélioration de leur qualité (remaillage) ou de leur simplification. Dans la littérature, le repositionnement des sommets d'un maillage est soit traité de manière locale, soit de manière globale mais sans un contrôle local de l'erreur géométrique introduite, i.e. les solutions actuelles ne sont pas globales ou introduisent de l'erreur géométrique non-contrôlée. Les techniques d'approximation de maillage les plus prometteuses se basent sur une décomposition en primitives géométriques simples (plans, cylindres, sphères etc.), mais elles n'arrivent généralement pas à trouver la décomposition optimale, celle qui optimise à la fois l'erreur géométrique de l'approximation par les primitives choisies, et le nombre et le type de ces primitives simples. Pour traiter les défauts des approches de remaillage existantes, nous proposons une méthode basée sur un modèle global, à savoir une modélisation graphique probabiliste, intégrant des contraintes souples basées sur la géométrie (l'erreur de l'approximation), la qualité du maillage et le nombre de sommets du maillage. De même, pour améliorer la décomposition en primitives simples, une modélisation graphique probabiliste a été choisie. Les modèles graphiques de cette thèse sont des champs aléatoires de Markov, ces derniers permettant de trouver une configuration optimale à l'aide de la minimisation globale d'une fonction objectif. Nous avons proposé trois contributions dans cette thèse autour des maillages triangulaires 2-variétés : (i) une méthode d'extraction statistiquement robuste des arêtes caractéristiques applicable aux objets mécaniques, (ii) un algorithme de segmentation en régions approximables par des primitives géométriques simples qui est robuste à la présence de données aberrantes et au bruit dans la position des sommets, (iii) et finalement un algorithme d'optimisation de maillages qui cherche le meilleur compromis entre l'amélioration de la qualité des triangles, la qualité de la valence des sommets, le nombre de sommets et la fidélité géométrique à la surface initiale. / The work in this thesis concerns structural analysis of 2-manifold triangular meshes, and their processing towards quality enhancement (remeshing) or simplification. In existing work, the repositioning of mesh vertices necessary for remeshing is either done locally or globally, but in the latter case without local control on the introduced geometrical error. Therefore, current results are either not globally optimal or introduce unwanted geometrical error. Other promising remeshing and approximation techniques are based on a decomposition into simple geometrical primitives (planes, cylinders, spheres etc.), but they generally fail to find the best decomposition, i.e. the one which jointly optimizes the residual geometrical error as well as the number and type of selected simple primitives. To tackle the weaknesses of existing remeshing approaches, we propose a method based on a global model, namely a probabilistic graphical model integrating soft constraints based on geometry (approximation error), mesh quality and the number of mesh vertices. In the same manner, for segmentation purposes and in order to improve algorithms delivering decompositions into simple primitives, a probabilistic graphical modeling has been chosen. The graphical models used in this work are Markov Random Fields, which allow to find an optimal configuration by a global minimization of an objective function. We have proposed three contributions in this thesis about 2-manifold triangular meshes : (i) a statistically robust method for feature edge extraction for mechanical objects, (ii) an algorithm for the segmentation into regions which are approximated by simple primitives, which is robust to outliers and to the presence of noise in the vertex positions, (iii) and lastly an algorithm for mesh optimization which jointly optimizes triangle quality, the quality of vertex valences, the number of vertices, as well as the geometrical fidelity to the initial surface.