O objetivo deste trabalho é apresentar algoritmos aplicados para extração de características invariantes à rotação em imagens de impressões digitais. No pré-processamento da imagem utiliza-se detecção de bordas pelo detector de Canny tendo como resultado uma imagem binarizada e afinada. Na extração das minúcias a metodologia adotada é o número de cruzamentos (CN), que extrai os aspectos locais, tais como, as minúcias fim de linha e bifurcações. A direção das cristas locais não é utilizada porque nas imagens rotacionadas a condição de permanência das propriedades biométricas não são satisfeitas. A comparação das impressões digitais utiliza os vetores gerados pela extração de minúcias considerando a posição (x,y) da minúcia armazenada em um vetor por tipo de minúcia (um vetor para crista final e outro vetor para crista bifurcada) e calculando a distância Euclidiana dessa posição (x,y) ao centro de massa da distribuição de minúcias para cada tipo de minúcia. Assim, as duas imagens são similares quando a distância Euclidiana entre os vetores de cada imagem e por tipo de minúcia forem mínimas. São discutidas as limitações de outros trabalhos existentes envolvendo rotação, translação e distorção da imagem de impressão digital, mostrando que os poucos trabalhos que tratam o problema possuem resultados não satisfatórios. Os maiores problemas ocorridos foram a extração de minúcias espúrias, mas foram resolvidos com os métodos sugeridos por Dixon (1979), tendo resultados satisfatórios em duas metodologias. No método média, a precisão para encontrar uma imagem foi de 100%, duas imagens 97,32%, três imagens 92,35%, quatro imagens 86,41% e cinco imagens 71,86%. E no método normal, a precisão para encontrar uma imagem foi de 100%, duas imagens 99,20%, três imagens 96,95%, quatro imagens 94,00% e cinco imagens 76,43%. / The objective of this research is to present algorithms that can be applied in fingerprints images in order to extract certain features, which are invariant to an likely rotation in the given image. In the preprocessing stage, the Canny border detector is used, resulting in a binary, fine tuned image. For the minutiae extraction, the crossing number method is used, which extracts local aspects such as minutiae endings and bifurcations. The direction of local ridges is ignored because, in rotated images, the permanence conditions of the biometric attributes are not fulfilled. The process of matching fingerprints uses two arrays (one for ridge endings and the other for bifurcations), which are generated by the extraction of the minutiae, considering the (x,y) coordinate of the given minutiae stored in the arrays, and calculating its Euclidian distance relating to the center of mass of the minutiae distribution, for each of its types (ending or bifurcation). Thus, both images are similar when the Euclidian distance between the arrays of each image, distinct by the type of each minutiae, is minimal. The limitations of other pieces of research works concerning fingerprint image rotation, translation and distortion are discussed, indicating that the only few ones that deal with these kinds of problems give unsatisfactory results.

Classificação de imagens de textura, especialmente aquelas com mudanças significativas de rotação, iluminação, escala e ponto de vista, é um problema fundamental e desafiador na área de visão computacional. Esta tese propõe dois descritores de imagem simples, porém eficientes, chamados de Sampled Local Mapped Pattern Magnitude (SLMP_M) e Completed Local Mapped Pattern (CLMP) aplicados na classificação de textura. Os descritores propostos são parte de um aprimoramento do descritor Local Mapped Pattern (LMP) para trabalhar de maneira eficiente com imagens de textura rotacionadas. Os métodos propostos necessitam de um pré-ajuste de parâmetros que utiliza o método de otimização por enxame de partículas, e são discriminativos e robustos para a descrição de texturas rotacionadas em ângulos arbitrários. Para a validação dos descritores propostos duas bases de imagens são utilizadas, Kylberg Sintorn Rotation Dataset e Brodatz Texture Rotation Dataset, uma nova base de dados desenvolvida pela autora, formada por imagens de texturas rotacionadas do Álbum de Brodatz. As duas bases contêm imagens de texturas naturais que foram rotacionadas fisicamente no momento da captura e rotacionadas por processos computacionais. É feita também uma avaliação da influência de métodos de interpolação no processo de rotação das imagens e são comparados com diferentes descritores presentes na literatura. Cinco métodos de interpolação são investigados: Lanczos, B-spline, Cúbica, Linear e Nearest Neighbor. Os resultados experimentais demonstram que os descritores propostos nesta tese superam o desempenho dos descritores Completed Local Binary Pattern (CLBP), e dos descritores que combinam a versão generalizada das características de Fourier com variações do descritor Local Binary Pattern (LBP), LBPDFT, ILBPDFT, LTPDFT e ILTPDFT. Os resultados também demonstram que a escolha do método de interpolação no processo de rotação das imagens influencia na capacidade de reconhecimento. / Texture image classification, especially those with significant changes of rotation, illumination, scale and point of view, is a fundamental and challenging problem in the field of computer vision. This thesis proposes two simple, but efficient, image descriptors called Sampled Local Mapped Pattern Magnitude (SLMP_M) and Completed Local Mapped Pattern (CLMP) applied in texture classification. The proposed descriptors are part of an enhancement to the Local Mapped Pattern (LMP) descriptor to work efficiently with rotated texture images. The descriptors proposed requires a parameter preset by the particle swarm optimization method, they are discriminating and robust for the description of rotated textures at arbitrary angles. For the validation of the proposed descriptors two image datasets are used: Kylberg Sintorn Rotation Dataset and Brodatz Texture Rotation Dataset, a new texture dataset introduced, which contains rotated texture images from Brodatzs Album. Both databases contain images of natural textures that have been rotated by Hardware and computational procedures. An evaluation of the influence of interpolation methods on the image rotation process is also presented and compared with different descriptors in the literature. Five interpolation methods are investigated: Lanczos, B-spline, Cubic, Linear and Nearest Neighbor. The experimental results show that the descriptors proposed in this thesis outperform the performance of the Completed Local Binary Pattern (CLBP) descriptors, and the descriptors that combine the generalized version of the Fourier characteristics with variations of the descriptor Local Binary Pattern (LBP), LBPDFT, ILBDFT, LTPDFT e ILTPDFT compared. The results also prove that the selection of the interpolation method in the image rotation process influences the recognition capability.

O objetivo deste trabalho é apresentar algoritmos aplicados para extração de características invariantes à rotação em imagens de impressões digitais. No pré-processamento da imagem utiliza-se detecção de bordas pelo detector de Canny tendo como resultado uma imagem binarizada e afinada. Na extração das minúcias a metodologia adotada é o número de cruzamentos (CN), que extrai os aspectos locais, tais como, as minúcias fim de linha e bifurcações. A direção das cristas locais não é utilizada porque nas imagens rotacionadas a condição de permanência das propriedades biométricas não são satisfeitas. A comparação das impressões digitais utiliza os vetores gerados pela extração de minúcias considerando a posição (x,y) da minúcia armazenada em um vetor por tipo de minúcia (um vetor para crista final e outro vetor para crista bifurcada) e calculando a distância Euclidiana dessa posição (x,y) ao centro de massa da distribuição de minúcias para cada tipo de minúcia. Assim, as duas imagens são similares quando a distância Euclidiana entre os vetores de cada imagem e por tipo de minúcia forem mínimas. São discutidas as limitações de outros trabalhos existentes envolvendo rotação, translação e distorção da imagem de impressão digital, mostrando que os poucos trabalhos que tratam o problema possuem resultados não satisfatórios. Os maiores problemas ocorridos foram a extração de minúcias espúrias, mas foram resolvidos com os métodos sugeridos por Dixon (1979), tendo resultados satisfatórios em duas metodologias. No método média, a precisão para encontrar uma imagem foi de 100%, duas imagens 97,32%, três imagens 92,35%, quatro imagens 86,41% e cinco imagens 71,86%. E no método normal, a precisão para encontrar uma imagem foi de 100%, duas imagens 99,20%, três imagens 96,95%, quatro imagens 94,00% e cinco imagens 76,43%. / The objective of this research is to present algorithms that can be applied in fingerprints images in order to extract certain features, which are invariant to an likely rotation in the given image. In the preprocessing stage, the Canny border detector is used, resulting in a binary, fine tuned image. For the minutiae extraction, the crossing number method is used, which extracts local aspects such as minutiae endings and bifurcations. The direction of local ridges is ignored because, in rotated images, the permanence conditions of the biometric attributes are not fulfilled. The process of matching fingerprints uses two arrays (one for ridge endings and the other for bifurcations), which are generated by the extraction of the minutiae, considering the (x,y) coordinate of the given minutiae stored in the arrays, and calculating its Euclidian distance relating to the center of mass of the minutiae distribution, for each of its types (ending or bifurcation). Thus, both images are similar when the Euclidian distance between the arrays of each image, distinct by the type of each minutiae, is minimal. The limitations of other pieces of research works concerning fingerprint image rotation, translation and distortion are discussed, indicating that the only few ones that deal with these kinds of problems give unsatisfactory results.

Classificação de imagens de textura, especialmente aquelas com mudanças significativas de rotação, iluminação, escala e ponto de vista, é um problema fundamental e desafiador na área de visão computacional. Esta tese propõe dois descritores de imagem simples, porém eficientes, chamados de Sampled Local Mapped Pattern Magnitude (SLMP_M) e Completed Local Mapped Pattern (CLMP) aplicados na classificação de textura. Os descritores propostos são parte de um aprimoramento do descritor Local Mapped Pattern (LMP) para trabalhar de maneira eficiente com imagens de textura rotacionadas. Os métodos propostos necessitam de um pré-ajuste de parâmetros que utiliza o método de otimização por enxame de partículas, e são discriminativos e robustos para a descrição de texturas rotacionadas em ângulos arbitrários. Para a validação dos descritores propostos duas bases de imagens são utilizadas, Kylberg Sintorn Rotation Dataset e Brodatz Texture Rotation Dataset, uma nova base de dados desenvolvida pela autora, formada por imagens de texturas rotacionadas do Álbum de Brodatz. As duas bases contêm imagens de texturas naturais que foram rotacionadas fisicamente no momento da captura e rotacionadas por processos computacionais. É feita também uma avaliação da influência de métodos de interpolação no processo de rotação das imagens e são comparados com diferentes descritores presentes na literatura. Cinco métodos de interpolação são investigados: Lanczos, B-spline, Cúbica, Linear e Nearest Neighbor. Os resultados experimentais demonstram que os descritores propostos nesta tese superam o desempenho dos descritores Completed Local Binary Pattern (CLBP), e dos descritores que combinam a versão generalizada das características de Fourier com variações do descritor Local Binary Pattern (LBP), LBPDFT, ILBPDFT, LTPDFT e ILTPDFT. Os resultados também demonstram que a escolha do método de interpolação no processo de rotação das imagens influencia na capacidade de reconhecimento. / Texture image classification, especially those with significant changes of rotation, illumination, scale and point of view, is a fundamental and challenging problem in the field of computer vision. This thesis proposes two simple, but efficient, image descriptors called Sampled Local Mapped Pattern Magnitude (SLMP_M) and Completed Local Mapped Pattern (CLMP) applied in texture classification. The proposed descriptors are part of an enhancement to the Local Mapped Pattern (LMP) descriptor to work efficiently with rotated texture images. The descriptors proposed requires a parameter preset by the particle swarm optimization method, they are discriminating and robust for the description of rotated textures at arbitrary angles. For the validation of the proposed descriptors two image datasets are used: Kylberg Sintorn Rotation Dataset and Brodatz Texture Rotation Dataset, a new texture dataset introduced, which contains rotated texture images from Brodatzs Album. Both databases contain images of natural textures that have been rotated by Hardware and computational procedures. An evaluation of the influence of interpolation methods on the image rotation process is also presented and compared with different descriptors in the literature. Five interpolation methods are investigated: Lanczos, B-spline, Cubic, Linear and Nearest Neighbor. The experimental results show that the descriptors proposed in this thesis outperform the performance of the Completed Local Binary Pattern (CLBP) descriptors, and the descriptors that combine the generalized version of the Fourier characteristics with variations of the descriptor Local Binary Pattern (LBP), LBPDFT, ILBDFT, LTPDFT e ILTPDFT compared. The results also prove that the selection of the interpolation method in the image rotation process influences the recognition capability.

This thesis addresses the task of developing automatic algorithms for analysing the two-dimensional ultrasound video footage obtained from fetal heart screening scans. These scans are typically performed in the second trimester of pregnancy to check for congenital heart anomalies and require significant training and anatomical knowledge to perform. The aim is to develop a tool that runs at high frame rates with no user initialisation and infers the visibility, position, orientation, view classification, and cardiac phase of the heart, and additionally the locations of cardiac structures of interest (such as valves and vessels) in a manner that is robust to the various sources of variation that occur in real-world ultrasound scanning. This is the first work to attempt such a detailed automated analysis of these videos. The problem is posed as a Bayesian filtering problem, which provides a principled framework for aggregating uncertain measurements across a number of frames whilst exploiting the constraints imposed by anatomical feasibility. The resulting inference problem is solved approximately with a particle filter, whose state space is partitioned to reduce the problems associated with filtering in high-dimensional spaces. Rotation-invariant features are captured from the videos in an efficient way in order to tackle the problem of unknown orientation. These are used within random forest learning models, including a novel formulation to predict circular-valued variables. The algorithm is validated on an annotated clinical dataset, and the results are compared to estimates of inter- and intra-observer variation, which are significant in both cases due to the inherent ambiguity in the imagery. The results suggest that the algorithm's output approaches these benchmarks in several respects, and fall slightly behind in others. The work presented here is an important first step towards developing automated clinical tools for the detection of congenital heart disease.

Ongoing expansion of digital images requires new methods for sorting, browsing, and sear- ching through huge image databases. This is a domain of Content-Based Image Retrieval (CBIR) systems, which are database search engines for images. A user typically submit a query image or series of images and the CBIR system tries to find and to retrieve the most similar images from the database. Optimally, the retrieved images should not be sensitive to circumstances during their acquisition. Unfortunately, the appearance of natural objects and materials is highly illumination and viewpoint dependent. This work focuses on representation and retrieval of homogeneous images, called textu- res, under the circumstances with variable illumination and texture rotation. We propose a novel illumination invariant textural features based on Markovian modelling of spatial tex- ture relations. The texture is modelled by Causal Autoregressive Random field (CAR) or Gaussian Markov Random Field (GMRF) models, which allow a very efficient estimation of its parameters, without the demanding Monte Carlo minimisation. Subsequently, the estimated model parameters are transformed into the new illumination invariants, which represent the texture. We derived that our textural representation is invariant to changes of illumination intensity and...

Résumé : En télédétection, la texture facilite l’identification des classes de surfaces sur des critères de similitude d’organisation spatiale des pixels. Les méthodes d’analyse texturale utilisées en télédétection et en traitement d’image en général sont principalement proposées pour extraire la texture dans une seule bande à la fois. Pour les images multispectrales, ceci revient à extraire la texture dans chaque bande spectrale séparément. Cette stratégie ignore la dépendance qui existe entre la texture des différentes bandes (texture inter-bande) qui peut être une source d’information additionnelle aux côtés de l’information texturale classique intra-bande. La prise en charge de la texture multibande (intra- et inter-bande) engendre une complexité calculatoire importante. Dans sa recherche de solution pour l’analyse de la texture multibande, ce projet de thèse revient vers les aspects fondamentaux de l’analyse de la texture, afin de proposer un modèle de texture qui possède intrinsèquement une complexité calculatoire réduite, et cela indépendamment de l’aspect multibande de la texture. Une solution pour la texture multibande est ensuite greffée sur ce nouveau modèle, de manière à lui permettre d’hériter de sa complexité calculatoire réduite. La première partie de ce projet de recherche introduit donc un nouveau modèle l’analyse de texture appelé modèle d’unité texturale compacte (en anglais : Compact Texture Unit, C-TU). Le C-TU prend comme point de départ le modèle de spectre de texture et propose une réduction significative de sa complexité. Cette réduction est atteinte en proposant une solution générale pour une codification de la texture avec la seule information d’occurrence, sans l’information structurelle. En prenant avantage de la grande efficacité calculatoire du modèle de C-TU développé, un nouvel indice qui analyse la texture multibande comme un ensemble indissociable d’interactions spatiales intra- et inter-bandes est proposé. Cet indice, dit C-TU multibande, utilise la notion de voisinage multibande afin de comparer le pixel central avec ses voisins dans la même bande et avec ceux des autres bandes spectrales. Ceci permet à l’indice de C-TU multibande d’extraire la texture de plusieurs bandes simultanément. Finalement, une nouvelle base de données de textures couleurs multibandes est proposée, pour une validation des méthodes texturales multibandes. Une série de tests visant principalement à évaluer la qualité discriminante des solutions proposées a été conduite. L’ensemble des résultats obtenus dont nous faisons rapport ici confirme que le modèle de C-TU proposé ainsi que sa version multibande sont des outils performants pour l’analyse de la texture en télédétection et en traitement d’images en général. Les tests ont également démontré que la nouvelle base de données de textures multibande possède toutes les caractéristiques nécessaires pour être utilisée en validation des méthodes de texture multibande. // Abstract : In multispectral images, texture is typically extracted independently in each band using existing grayscale texture methods. However, reducing texture of multispectral images into a set of independent grayscale texture ignores inter-band spatial interactions which can be a valuable source of information. The main obstacle for characterizing texture as intra- and inter-band spatial interactions is that the required calculations are cumbersome. In the first part of this PhD thesis, a new texture model named the Compact Texture Unit (C-TU) model was proposed. The C-TU model is a general solution for the texture spectrum model, in order to decrease its computational complexity. This simplification comes from the fact that the C-TU model characterizes texture using only statistical information, while the texture spectrum model uses both statistical and structural information. The proposed model was evaluated using a new monoband C-TU descriptor in the context of texture classification and image retrieval. Results showed that the monoband C-TU descriptor that uses the proposed C-TU model provides performances equivalent to those delivered by the texture spectrum model but with much more lower complexity. The calculation efficiency of the proposed C-TU model is exploited in the second part of this thesis in order to propose a new descriptor for multiband texture characterization. This descriptor, named multiband C-TU, extracts texture as a set of intra- and inter-band spatial interactions simultaneously. The multiband C-TU descriptor is very simple to extract and computationally efficient. The proposed descriptor was compared with three strategies commonly adopted in remote sensing. The first is extracting texture using panchromatic data; the second is extracting texture separately from few newbands obtained by principal components transform; and the third is extracting texture separately in each spectral band. These strategies were applied using cooccurrence matrix and monoband compact texture descriptors. For all experiments, the proposed descriptor provided the best results. In the last part of this thesis, a new color texture images database is developed, named Multiband Brodatz Texture database. Images from this database have two important characteristics. First, their chromatic content, even if it is rich, does not have discriminative value, yet it contributes to form texture. Second, their textural content is characterized by high intra- and inter-band variation. These two characteristics make this database ideal for multiband texture analysis without the influence of color information.

This PhD thesis deals with the use of structural methods of objects identification for industrial robots operation. First, the present state of knowledge in the field is described, i.e. the whole process of objects recognition with the aid of common methods of the syntactic analysis. The main disadvantage of these methods is that is impossible to recognize objects whose digitalized image is corrupted in some ways (due to excessive noise or image disturbances), objects are therefore deformed. Further, other methods for the recognition of deformed objects are described. These methods use structural description of objects for object recognition, i.e. methods which determine the distance between attribute descriptions of images. The core part of this PhD thesis begins in Chapter 5, where deformation grammars, capable of description of all possible object deformations, are described. The only complication in the analysis is the ambiguity of the deformation grammar, which lowers the effectiveness of the analysis. Further, PhD thesis deals with the selection and modification of a proper parser, which is able to analyze a deformation grammar effectively. Three parsers are described: the modified Earley parser, the modified Tomita parser and the modified hybrid LRE(k) parser. As for the modified Earley’s parser, ways of its effective implementation are described. One of the necessary parts of the object recognition is providing the invariances, which this PhD thesis covers in detail, too. Finally, the results of described algorithms are mentioned (successfulness and speed of deformed objects recognition) and suggested testing environment and implemented algorithms are described. In conclusion, all determined possibilities of deformation grammars and their results are summarized.