A análise da retina permite o diagnostico de muitas patologias relacionadas ao olho humano. A qualidade da imagem e um fator importante já que o médico normalmente examina os pequenos vasos da retina e a sua coloração. O equipamento normalmente utilizado para a visualização da retina e o retinógrafo digital, que utiliza sensor colorido com filtro de Bayer e luz (flash) branca. No entanto, esse filtro causa perda na resolução espacial, uma vez que e necessário um processo de interpolação matemática para a formação da imagem. Com o objetivo de melhorar a qualidade da imagem da retina, um retinógrafo com câmera CCD monocromática de alta resolução foi desenvolvido. Nele, as imagens coloridas são geradas pela combinação dos canais monocromáticos R (vermelho), G (verde) e B (azul), adquiridos com o chaveamento da iluminação do olho com LED vermelho, verde e azul, respectivamente. Entretanto, o pequeno período entre os flashes pode causar desalinhamento entre os canais devido a pequenos movimentos do olho. Assim, este trabalho apresenta uma técnica de registro de imagens, baseado em correlação de fase no domínio da frequência, para realizar precisamente o alinhamento dos canais RGB no processo de geração de imagens coloridas da retina. A validação do método foi realizada com um olho mecânico (phantom) para a geração de 50 imagens desalinhadas que foram corrigidas pelo método proposto e comparadas com as imagens alinhadas obtidas como referência (ground-truth). Os resultados mostraram que retinógrafo com câmera monocromática e o método de registro proposto nesse trabalho podem produzir imagens coloridas da retina com alta resolução espacial, sem a perda de qualidade intrínseca às câmeras CCD coloridas que utilizam o filtro de Bayer. / The analysis of retina allows the diagnostics of several pathologies related to the human eye. Image quality is an important factor since the physician often examines the small vessels of the retina and its color. The device usually used to observe the retina is the fundus camera, which uses color sensor with Bayer filter and white light. However, this filter causes loss of spatial resolution, since it is necessary a mathematical interpolation process to create the final image. Aiming at improving the retina image quality, a fundus camera with monochromatic CCD camera was developed. In this device, color images are generated by combining the monochromatic channels R (red), G (green) and B (blue), which were acquired by switching the eye illumination with red, green and blue light, respectively. However, the short period between the flashes may cause misalignment among the channels because of the small movements of the eye. Thus, this work presents an image registration technique based on phase correlation in the frequency domain, for accurately aligning the RGB channels on the process of generating retina color images. Validation of the method was performed by using a mechanical eye (phantom) for generating 50 misaligned images, which were aligned by the proposed method and compared to the aligned images obtained as references (ground-truth). Results showed that the fundus camera with monochromatic camera and the method proposed in this work can produce high spatial resolution images without the loss of quality intrinsic to color CCD cameras that uses Bayer filter.

La couleur est un critère important dans de nombreux secteurs d'activité pour identifier, comparer ou encore contrôler la qualité de produits. Cette tâche est souvent assumée par un opérateur humain qui effectue un contrôle visuel. Malheureusement la subjectivité de celui-ci rend ces contrôles peu fiables ou répétables. Pour contourner ces limitations, l'utilisation d'une caméra RGB permet d'acquérir et d'extraire des propriétés photométriques. Cette solution est facile à mettre en place et offre une rapidité de contrôle. Cependant, elle est sensible au phénomène de métamérisme. La mesure de réflectance spectrale est alors la solution la plus appropriée pour s'assurer de la conformité colorimétrique entre des échantillons et une référence. Ainsi dans l'imprimerie, des spectrophotomètres sont utilisés pour mesurer des patchs uniformes imprimés sur une bande latérale. Pour contrôler l'ensemble d'une surface imprimée, des caméras multi-spectrales sont utilisées pour estimer la réflectance de chaque pixel. Cependant, elles sont couteuses comparées aux caméras conventionnelles. Dans ces travaux de recherche, nous étudions l'utilisation d'une caméra RGB pour l'estimation de la réflectance dans le cadre de l'imprimerie. Nous proposons une description spectrale complète de la chaîne de reproduction pour réduire le nombre de mesures dans les phases d'apprentissage et pour compenser les limitations de l'acquisition. Notre première contribution concerne la prise en compte des limitations colorimétriques lors de la caractérisation spectrale d'une caméra. La deuxième contribution est l'exploitation du modèle spectrale de l'imprimante dans les méthodes d'estimation de réflectance. / Color is a major criterion for many sectors to identify, to compare or simply to control the quality of products. This task is generally assumed by a human operator who performs a visual inspection. Unfortunately, this method is unreliable and not repeatable due to the subjectivity of the operator. To avoid these limitations, a RGB camera can be used to capture and extract the photometric properties. This method is simple to deploy and permits a high speed control. However, it's very sensitive to the metamerism effects. Therefore, the reflectance measurement is the more reliable solution to ensure the conformity between samples and a reference. Thus in printing industry, spectrophotometers are used to measure uniform color patches printed on a lateral band. For a control of the entire printed surface, multispectral cameras are used to estimate the reflectance of each pixel. However, they are very expensive compared to conventional cameras. In this thesis, we study the use of an RGB camera for the spectral reflectance estimation in the context of printing. We propose a complete spectral description of the reproduction chain to reduce the number of measurements in the training stages and to compensate for the acquisition limitations. Our first main contribution concerns the consideration of the colorimetric limitations in the spectral characterization of a camera. The second main contribution is the exploitation of the spectral printer model in the reflectance estimation methods.

Pattern recognition has as its objective to classify objects into different categories and classes. It is a fundamental component of artificial intelligence and computer vision. This thesis investigates the application of an efficient optimization method, known as Particle Swarm Optimization (PSO), to the field of pattern recognition and image processing. First a clustering method that is based on PSO is proposed. The application of the proposed clustering algorithm to the problem of unsupervised classification and segmentation of images is investigated. A new automatic image generation tool tailored specifically for the verification and comparison of various unsupervised image classification algorithms is then developed. A dynamic clustering algorithm which automatically determines the "optimum" number of clusters and simultaneously clusters the data set with minimal user interference is then developed. Finally, PSO-based approaches are proposed to tackle the color image quantization and spectral unmixing problems. In all the proposed approaches, the influence of PSO parameters on the performance of the proposed algorithms is evaluated. / Thesis (PhD)--University of Pretoria, 2006. / Computer Science / unrestricted

Dans ce manuscrit, nous avons étudié l’extension de l’analyse multi-résolution aux images couleurs par des transformées sur graphe. Dans ce cadre, nous avons déployé trois stratégies d’analyse différentes. En premier lieu, nous avons défini une transformée basée sur l’utilisation d’un graphe perceptuel dans l’analyse à travers la transformé en ondelettes spectrale sur graphe. L’application en débruitage d’image met en évidence l’utilisation du SVH dans l’analyse des images couleurs. La deuxième stratégie consiste à proposer une nouvelle méthode d’inpainting pour des images couleurs. Pour cela, nous avons proposé un schéma de régularisation à travers les coefficients d’ondelettes de la TOSG, l’estimation de la structure manquante se fait par la construction d’un graphe des patchs couleurs à partir des moyenne non locales. Les résultats obtenus sont très encourageants et mettent en évidence l’importance de la prise en compte du SVH. Dans la troisième stratégie, nous proposons une nouvelleapproche de décomposition d’un signal défini sur un graphe complet. Cette méthode est basée sur l’utilisation des propriétés de la matrice laplacienne associée au graphe complet. Dans le contexte des images couleurs, la prise en compte de la dimension couleur est indispensable pour pouvoir identifier les singularités liées à l’image. Cette dernière offre de nouvelles perspectives pour une étude approfondie de son comportement. / In our work, we studied the extension of the multi-resolution analysis for color images by using transforms on graphs. In this context, we deployed three different strategies of analysis. Our first approach consists of computing the graph of an image using the psychovisual information and analyzing it by using the spectral graph wavelet transform. We thus have defined a wavelet transform based on a graph with perceptual information by using the CIELab color distance. Results in image restoration highlight the interest of the appropriate use of color information. In the second strategy, we propose a novel recovery algorithm for image inpainting represented in the graph domain. Motivated by the efficiency of the wavelet regularization schemes and the success of the nonlocal means methods we construct an algorithm based on the recovery of information in the graph wavelet domain. At each step the damaged structure are estimated by computing the non local graph then we apply the graph wavelet regularization model using the SGWT coefficient. The results are very encouraging and highlight the use of the perceptual informations. In the last strategy, we propose a new approach of decomposition for signals defined on a complete graphs. This method is based on the exploitation of of the laplacian matrix proprieties of the complete graph. In the context of image processing, the use of the color distance is essential to identify the specificities of the color image. This approach opens new perspectives for an in-depth study of its behavior.

Úlceras de pele são causadas devido à deficiência na circulação sanguínea. O diagnóstico é feito pela análise visual das regiões afetadas. A quantificação da distribuição de cores da lesão, por meio de técnicas de processamento de imagens pode auxiliar na caracterização e análise da dinâmica do processo patológico e resposta ao tratamento. O processamento de imagens de úlceras dermatológicas envolve etapas relacionadas a segmentação, caracterização e indexação. Esta análise é importante para classificação, recuperação de imagens similares e acompanhamento da evolução de uma lesão. Este trabalho apresenta um estudo sobre técnicas de segmentação e caracterização de imagens coloridas de úlceras de pele, baseadas nos modelos de cores RGB, HSV, L*a*b* e L*u*v*, utilizando suas componentes na extração de informações de textura e cor. Foram utilizadas técnicas de Aprendizado de Máquina e algoritmos matemáticos para a segmentação e extração de atributos, utilizando uma base de dados com 172 imagens. Nos testes de recuperação, foram utilizadas diferentes métricas de distância para avaliação do desempenho e técnicas de seleção de atributos. Os resultados obtidos evidenciam bom potencial para apoio ao diagnóstico e acompanhamento da evolução do tratamento com valores de até 75% de precisão para as técnicas de recuperação, 0,9 de área embaixo da curva receiver-operating-characteristic na classificação e 0,04 de erro médio quadrático entre a composição de cores da imagem segmentada automaticamente e a segmentada manualmente. Nos testes utilizando seleção de atributos, foi observado uma redução nos valores de precisão de recuperação (60%) e valores similares nos tetes de classificação (0,85). / Skin ulcers are caused due to deficiency in the bloodstream. The diagnosis is made by a visual analysis of the affected area. Quantification of color distribution of the lesion by image processing techniques can aid in the characterization and response to treatment. The image processing steps involves skin ulcers related to segmentation, characterization and indexing. This analysis is important for classification, image retrieval and similar tracking the evolution of an injury. This project presents a study of segmentation techniques and characterization of color images of dermatological skin ulcers, based on the color models RGB, HSV, L*a*b* and L*u*v*, using their components in the extraction of texture and color information. Were used Machine Learning techniques, mathematical algorithms for segmentation and extraction of attributes, using a database containing 172 images in two versions. In recovery tests were used different distance metrics for performance evaluation and techniques of features selection. The results show good potential to support the diagnosis and monitoring of treatment progress with values up to 75% precision in recovery techniques, 0.9 area under the curve receiver-operating-characteristic) in classification, and 0.04 mean square error between the color composition of the automatically segmented image and the manually segmented image. In tests utilizing feature selection was observed a decrease in precision values of image retrieval (60%) and similar values in the classification\'s tests (0.85).

Ces travaux de recherche concernent la modélisation de l'information dynamique fonctionnelle fournie par les champs de déplacements apparents à l'aide de base de polynômes orthogonaux. Leur objectif est de modéliser le mouvement et la texture extraites afin de l'exploiter dans les domaines de l'analyse et de la reconnaissance automatique d'images et de vidéos. Nous nous intéressons aussi bien aux mouvements humains qu'aux textures dynamiques. Les bases de polynômes orthogonales ont été étudiées. Cette approche est particulièrement intéressante car elle offre une décomposition en multi-résolution et aussi en multi-échelle. La première contribution de cette thèse est la définition d'une méthode spatiale de décomposition d'image : l'image est projetée et reconstruite partiellement avec un choix approprié du degré d'anisotropie associé à l'équation de décomposition basée sur des transformations polynomiales. Cette approche spatiale est étendue en trois dimensions afin d'extraire la texture dynamique dans des vidéos. Notre deuxième contribution consiste à utiliser les séquences d'images qui représentent les parties géométriques comme images initiales pour extraire les flots optiques couleurs. Deux descripteurs d'action, spatial et spatio-temporel, fondés sur la combinaison des informations du mouvement/texture sont alors extraits. Il est ainsi possible de définir un système permettant de reconnaître une action complexe (composée d'une suite de champs de déplacement et de textures polynomiales) dans une vidéo. / The research relies on modeling the dynamic functional information from the fields of apparent movement using basic orthogonal polynomials. The goal is to model the movement and texture extracted for automatic analysis and recognition of images and videos. We are interested both in human movements as dynamic textures. Orthogonal polynomials bases were studied. This approach is particularly interesting because it offers a multi-resolution and a multi-scale decomposition. The first contribution of this thesis is the definition of method of image spatial decomposition: the image is projected and partially rebuilt with an appropriate choice of the degree of anisotropy associated with the decomposition equation based on polynomial transformations. This spatial approach is extended into three dimensions to retrieve the dynamic texture in videos. Our second contribution is to use image sequences that represent the geometric parts as initial images to extract color optical flow. Two descriptors of action, spatial and space-time, based on the combination of information of motion / texture are extracted. It is thus possible to define a system to recognize a complex action (composed of a series of fields of motion and polynomial texture) in a video.

Úlceras de pele são causadas devido à deficiência na circulação sanguínea. O diagnóstico é feito pela análise visual das regiões afetadas. A quantificação da distribuição de cores da lesão, por meio de técnicas de processamento de imagens pode auxiliar na caracterização e análise da dinâmica do processo patológico e resposta ao tratamento. O processamento de imagens de úlceras dermatológicas envolve etapas relacionadas a segmentação, caracterização e indexação. Esta análise é importante para classificação, recuperação de imagens similares e acompanhamento da evolução de uma lesão. Este trabalho apresenta um estudo sobre técnicas de segmentação e caracterização de imagens coloridas de úlceras de pele, baseadas nos modelos de cores RGB, HSV, L*a*b* e L*u*v*, utilizando suas componentes na extração de informações de textura e cor. Foram utilizadas técnicas de Aprendizado de Máquina e algoritmos matemáticos para a segmentação e extração de atributos, utilizando uma base de dados com 172 imagens. Nos testes de recuperação, foram utilizadas diferentes métricas de distância para avaliação do desempenho e técnicas de seleção de atributos. Os resultados obtidos evidenciam bom potencial para apoio ao diagnóstico e acompanhamento da evolução do tratamento com valores de até 75% de precisão para as técnicas de recuperação, 0,9 de área embaixo da curva receiver-operating-characteristic na classificação e 0,04 de erro médio quadrático entre a composição de cores da imagem segmentada automaticamente e a segmentada manualmente. Nos testes utilizando seleção de atributos, foi observado uma redução nos valores de precisão de recuperação (60%) e valores similares nos tetes de classificação (0,85). / Skin ulcers are caused due to deficiency in the bloodstream. The diagnosis is made by a visual analysis of the affected area. Quantification of color distribution of the lesion by image processing techniques can aid in the characterization and response to treatment. The image processing steps involves skin ulcers related to segmentation, characterization and indexing. This analysis is important for classification, image retrieval and similar tracking the evolution of an injury. This project presents a study of segmentation techniques and characterization of color images of dermatological skin ulcers, based on the color models RGB, HSV, L*a*b* and L*u*v*, using their components in the extraction of texture and color information. Were used Machine Learning techniques, mathematical algorithms for segmentation and extraction of attributes, using a database containing 172 images in two versions. In recovery tests were used different distance metrics for performance evaluation and techniques of features selection. The results show good potential to support the diagnosis and monitoring of treatment progress with values up to 75% precision in recovery techniques, 0.9 area under the curve receiver-operating-characteristic) in classification, and 0.04 mean square error between the color composition of the automatically segmented image and the manually segmented image. In tests utilizing feature selection was observed a decrease in precision values of image retrieval (60%) and similar values in the classification\'s tests (0.85).

Abstract Image acquisition devices are always subject to physical limitations that often manifest as distortions in the appearance of the captured image. The most common types of distortions can be divided into two categories: geometric and radiometric distortions. Examples of the latter ones are: changes in brightness, contrast, or illumination, sensor noise and blur. Since image blur can have many different causes, it is usually not convenient and also computationally expensive to develop ad hoc algorithms to correct each specific type of blur. Instead, it is often possible to extract a blur-invariant representation of the image, and utilize such information to make algorithms that are insensitive to blur. The work presented here mainly focuses on developing techniques for the extraction and the application of blur-invariant operators. This thesis contains several contributions. First, we propose a generalized framework based on group theory to constructively generate complete blur-invariants. We construct novel operators that are invariant to a large family of blurs occurring in real scenarios: namely, those blurs that can be modeled by a convolution with a point-spread function having rotational symmetry, or combined rotational and axial symmetry. A second important contribution is represented by the utilization of such operators to develop an algorithm for blur-invariant translational image registration. This algorithm is experimentally demonstrated to be more robust than other state-of-the-art registration techniques. The blur-invariant registration algorithm is then used as pre-processing steps to several restoration methods based on image fusion, like depth-of-field extension, and multi-channel blind deconvolution. All the described techniques are then re-interpreted as a particular instance of Wiener deconvolution filtering. Thus, the third main contribution is the generalization of the blur-invariants and the registration techniques to color images, by using respectively a representation of color images based on quaternions, and the quaternion Wiener filter. This leads to the development of a blur-and-noise-robust registration algorithm for color images. We observe experimentally a significant increase in performance in both color texture recognition, and in blurred color image registration. / Tiivistelmä Kuvauslaitteet ovat aina fyysisten olosuhteiden rajoittamia, mikä usein ilmenee tallennetun kuvan ilmiasun vääristyminä. Yleisimmät vääristymätyypit voidaan jakaa kahteen kategoriaan: geometrisiin ja radiometrisiin distortioihin. Jälkimmäisestä esimerkkejä ovat kirkkauden, kontrastin ja valon laadun muutokset sekä sensorin kohina ja kuvan sumeus. Koska kuvan sumeus voi johtua monista tekijöistä, yleensä ei ole tarkoitukseen sopivaa eikä laskennallisesti kannattavaa kehittää ad hoc algoritmeja erityyppisten sumeuksien korjaamiseen. Sitä vastoin on mahdollista erottaa kuvasta sumeuden invariantin edustuma ja käyttää tätä tietoa sumeudelle epäherkkien algoritmien tuottamiseen. Tässä väitöskirjassa keskitytään esittämään, millaisia eri tekniikoita voidaan käyttää sumeuden invarianttien operaattoreiden muodostamiseen ja sovellusten kehittämiseen. Tämä opinnäyte sisältää useammanlaista tieteellistä vaikuttavuutta. Ensiksi, väitöskirjassa esitellään ryhmäteoriaan perustuva yleinen viitekehys, jolla voidaan generoida sumeuden invariantteja. Konstruoimme uudentyyppisiä operaattoreita, jotka ovat monenlaiselle kuvaustilanteessa ilmenevälle sumeudelle invariantteja. Kyseessä ovat ne rotationaalisesti (ja/tai aksiaalisesti) symmetrisen sumeuden lajit, jotka voidaan mallintaa pistelähteen hajaantumisen funktion (PSF) konvoluutiolla. Toinen tämän väitöskirjan tärkeä tutkimuksellinen anti on esitettyjen sumeuden invarianttien operaattoreiden hyödyntäminen algoritmin kehittelyssä, joka on käytössä translatorisen kuvan rekisteröinnissä. Tällainen algoritmi on tässä tutkimuksessa osoitettu kokeellisesti johtavia kuvien rekisteröintitekniikoita robustimmaksi. Sumeuden invariantin rekisteröinnin algoritmia on käytetty esiprosessointina tässä tutkimuksessa useissa kuvien restaurointimenetelmissä, jotka perustuvat kuvan fuusioon, kuten syväterävyysaluelaajennus ja monikanavainen dekonvoluutio. Kaikki kuvatut tekniikat ovat lopulta uudelleen tulkittu erityistapauksena Wienerin dekonvoluution suodattimesta. Näin ollen tutkimuksen kolmas saavutus on sumeuden invarianttien ja rekisteröintiteknikoiden yleistäminen värikuviin käyttämällä värikuvien kvaternion edustumaa sekä Wienerin kvaternion suodatinta. Havaitsemme kokeellisesti merkittävän parannuksen sekä väritekstuurin tunnistuksessa että sumean kuvan rekisteröinnissä.

Το ερευνητικό αντικείμενο της συγκεκριμένης διατριβής αναφέρεται στην επεξεργασία έγχρωμης εικόνας με χρήση της θεωρίας γράφων, την ανάκτηση εικόνας καθώς και την οργάνωση / διαχείριση βάσεων δεδομένων με μεθόδους γραφημάτων και αναγνώρισης προτύπων, με εφαρμογή σε πολυμέσα. Τα συγκεκριμένα προβλήματα προσεγγίστηκαν διατηρώντας τη γενικότητά τους και επιλύθηκαν με βάση τα ακόλουθα σημεία: 1. Ανάπτυξη τεχνικών για την επιλογή χαρακτηριστικών από τις εικόνες βάσει χαρακτηριστικών χαμηλού επιπέδου (χρώματος και υφής), για χρήση τους σε εφαρμογές ομοιότητας και ανάκτησης εικόνας. 2. Υπολογισμός μετρικών και αποστάσεων στο χώρο των χαρακτηριστικών. 3. Μελέτη της πολυσχιδούς δομής των εικόνων μιας βάσης στο χώρο των χαρακτηριστικών. 4. Ελάττωση της διάστασης του χώρου και παραγωγή αναπαραστάσεων δύο διαστάσεων. 5. Εφαρμογή των μεθόδων αυτών σε υποκειμενικές αποστάσεις εικόνων. Η θεωρία γράφων και οι μέθοδοι αναγνώρισης προτύπων χρησιμοποιήθηκαν προκειμένου να παρουσιαστούν βέλτιστες λύσεις αφενός στο πρόβλημα της ανάκτησης εικόνων από βάσεις δεδομένων και αφετέρου στην οργάνωση και διαχείριση τέτοιων βάσεων εικόνων. Η διατριβή φέρνει πιο κοντά την επεξεργασία εικόνας με μεθόδους προερχόμενες από τη θεωρία γραφημάτων, τη στατιστική και την αναγνώριση προτύπων. Σε όλη τη διάρκεια της διατριβής, ιδιαίτερη έμφαση δόθηκε στο ζήτημα της εύρεσης του κατάλληλου συνδυασμού μεταξύ της αποτελεσματικότητας των συστημάτων και της αποδοτικότητας στα πλαίσια της εφαρμογής των προτεινόμενων αλγοριθμικών διαδικασιών. Τα αναλυτικά πειραματικά αποτελέσματα που πραγματοποιήθηκαν, αποδεικνύουν την βελτιωμένη απόδοση των προτεινόμενων μεθοδολογιών. / The subject of this doctoral thesis is related to color image processing using graph theoretic methods, image retrieval and image database management and organization in the reduced feature space, using pattern recognition analysis, with multimedia applications. The author attempted to approach the thesis subject by retaining its genericness and addressing the following points: 1. Development of techniques for extraction of image visual attributes based on low level features (color and texture information), to be used for image similarity and retrieval practices. 2. Calculation of metrics and distances in the feature space. 3. Study of the image manifolds created in the selected feature space. 4. Application of dimensionality reduction techniques and production of biplots. 5. Application of the proposed methodologies using perceptual image distances. Graph theory and pattern recognition methodologies were incorporated in order to provide novel solution to color image retrieval of image databases, as well as to image database management and organization. The current thesis brings closer image processing with graph theoretic methodologies, statistical analysis and pattern recognition. Throughout the thesis, consideration has been taken for finding the best trade off between effectiveness and efficiency when applying the proposed algorithmic procedures. The extended experimental results carried out in all stages of the projected studies reveal the enhanced performance of the proposed methodologies.

This thesis consider description of segments identified in image. At first there are described main methods of segmentation because it is a process contiguous before describing of objects. Next chapter is devoted to methods which focus on description identified regions. There are studied algorithms used for characterizing of different features. There are parts devoted to color, location, size, orientation, shape and topology. The end of this chapter is devoted to moments. Next chapters are focused on designing fit algorithms for segments description and XML files creating according to MPEG-7 standards and their implementation into RapidMiner. In the last chapter there are described results of the implementation.