A classificação de texturas coloridas sob diferentes condições de iluminação é um desafio na área de visão computacional, e depende da eficiência dos descritores de textura em capturar características que sejam discriminantes independentemente das propriedades da fonte de luz incidente sobre o objeto. Visando melhorar o processo de classificação de texturas coloridas iluminadas com diferentes fontes de luz, este trabalho propõe três novos descritores, nomeados Opponent Color Local Mapped Pattern (OCLMP), que combina o descritor de texturas por padrões locais mapeados (Local Mapped Pattern - LMP) com a teoria de cores oponentes; Color Intensity Local Mapped Pattern (CILMP), que extrai as informações de cor e textura de maneira integrada, levando em consideração a textura da cor, combinando estas informações com características da luminância da textura em uma análise multiresolução; e Extended Color Local Mapped Pattern (ECLMP), que utiliza dois operadores para extrair informações de cor e textura de forma integrada (textura da cor) combinadas com informações apenas de textura (sem cor) de uma imagem. Todos esses novos descritores propostos são paramétricos e, sendo o ajuste ótimo de seus parâmetros não trivial, o processo exige um tempo excessivo de computação. Portanto, foi proposto nesta tese a utilização de algoritmos genéticos para o ajuste automático dos parâmetros. A avaliação dos descritores propostos foi realizada em duas bases de dados de texturas coloridas com variação de iluminação: RawFooT (Raw Food Texture Database) e KTH-TIPS- 2b (Textures under varying Illumination, Pose and Scale Database), utilizando-se um classificador. Os resultados experimentais mostraram que os descritores propostos são mais robustos à variação de iluminação do que outros decritores de textura comumente utilizados na literatura. Os descritores propostos apresentaram um desempenho superior aos descritores comparados em 15% na base de dados RawFooT e 4% na base de dados KTH-TIPS-2b. / Color texture classification under varying illumination remains a challenge in the computer vision field, and it greatly relies on the efficiency at which the texture descriptors capture discriminant features, independent of the illumination condition. The aim of this thesis is to improve the classification of color texture acquired with varying illumination sources. We propose three new color texture descriptors, namely: the Opponent Color Local Mapped Pattern (OCLMP), which combines a local methodology (LMP) with the opponent colors theory, the Color Intensity Local Mapped Pattern (CILMP), which extracts color and texture information jointly, in a multi-resolution fashion, and the Extended Color Local Mapped Pattern (ECLMP), which applies two operators to extract color and texture information jointly as well. As the proposed methods are based on the LMP algorithm, they are parametric functions. Finding the optimal set of parameters for the descriptor can be a cumbersome task. Therefore, this work proposes the use of genetic algorithms to automatically adjust the parameters. The methods were assessed using two data sets of textures acquired using varying illumination sources: the RawFooT (Raw Food Texture Database), and the KTH-TIPS-2b (Textures under varying Illumination, Pose and Scale Database). The experimental results show that the proposed descriptors are more robust to variations to the illumination source than other methods found in the literature. The improvement on the accuracy was higher than 15% on the RawFoot data set, and higher than 4% on the KTH-TIPS-2b data set.

A classificação de texturas coloridas sob diferentes condições de iluminação é um desafio na área de visão computacional, e depende da eficiência dos descritores de textura em capturar características que sejam discriminantes independentemente das propriedades da fonte de luz incidente sobre o objeto. Visando melhorar o processo de classificação de texturas coloridas iluminadas com diferentes fontes de luz, este trabalho propõe três novos descritores, nomeados Opponent Color Local Mapped Pattern (OCLMP), que combina o descritor de texturas por padrões locais mapeados (Local Mapped Pattern - LMP) com a teoria de cores oponentes; Color Intensity Local Mapped Pattern (CILMP), que extrai as informações de cor e textura de maneira integrada, levando em consideração a textura da cor, combinando estas informações com características da luminância da textura em uma análise multiresolução; e Extended Color Local Mapped Pattern (ECLMP), que utiliza dois operadores para extrair informações de cor e textura de forma integrada (textura da cor) combinadas com informações apenas de textura (sem cor) de uma imagem. Todos esses novos descritores propostos são paramétricos e, sendo o ajuste ótimo de seus parâmetros não trivial, o processo exige um tempo excessivo de computação. Portanto, foi proposto nesta tese a utilização de algoritmos genéticos para o ajuste automático dos parâmetros. A avaliação dos descritores propostos foi realizada em duas bases de dados de texturas coloridas com variação de iluminação: RawFooT (Raw Food Texture Database) e KTH-TIPS- 2b (Textures under varying Illumination, Pose and Scale Database), utilizando-se um classificador. Os resultados experimentais mostraram que os descritores propostos são mais robustos à variação de iluminação do que outros decritores de textura comumente utilizados na literatura. Os descritores propostos apresentaram um desempenho superior aos descritores comparados em 15% na base de dados RawFooT e 4% na base de dados KTH-TIPS-2b. / Color texture classification under varying illumination remains a challenge in the computer vision field, and it greatly relies on the efficiency at which the texture descriptors capture discriminant features, independent of the illumination condition. The aim of this thesis is to improve the classification of color texture acquired with varying illumination sources. We propose three new color texture descriptors, namely: the Opponent Color Local Mapped Pattern (OCLMP), which combines a local methodology (LMP) with the opponent colors theory, the Color Intensity Local Mapped Pattern (CILMP), which extracts color and texture information jointly, in a multi-resolution fashion, and the Extended Color Local Mapped Pattern (ECLMP), which applies two operators to extract color and texture information jointly as well. As the proposed methods are based on the LMP algorithm, they are parametric functions. Finding the optimal set of parameters for the descriptor can be a cumbersome task. Therefore, this work proposes the use of genetic algorithms to automatically adjust the parameters. The methods were assessed using two data sets of textures acquired using varying illumination sources: the RawFooT (Raw Food Texture Database), and the KTH-TIPS-2b (Textures under varying Illumination, Pose and Scale Database). The experimental results show that the proposed descriptors are more robust to variations to the illumination source than other methods found in the literature. The improvement on the accuracy was higher than 15% on the RawFoot data set, and higher than 4% on the KTH-TIPS-2b data set.

Este projeto descreve o desenvolvimento, estudo e aplicação de descritores fractais em análise de texturas. Nos últimos anos, a literatura vem apresentando a geometria fractal como uma ferramenta poderosa para a análise de imagens, com aplicações em variados campos da ciência. A maior parte destes trabalhos faz uso direto da dimensão fractal como um descritor do objeto representado na imagem. Entretanto, em função da complexidade de muitos problemas nesta área, algumas soluções foram propostas para melhorar essa análise, usando não apenas o valor da dimensão fractal, mas um conjunto de medidas que pudessem ser extraídas pela geometria fractal e que descrevessem as texturas com maior riqueza e precisão. Entre essas técnicas, destacam-se a metodologia de multifractais, de dimensão fractal multiescala e, mais recentemente, os descritores fractais. Esta última técnica tem se mostrado eficiente na solução de problemas relacionados à discriminação de imagens de texturas e formas, uma vez que os descritores gerados fornecem uma representação direta do padrão de complexidade (distribuição dos detalhes ao longo das escalas de observação) da imagem. Assim, essa solução permite que se tenha uma descrição rica da imagem estudada pela análise da distribuição espacial e/ou espectral dos pixels e intensidade de cores/tons de cinza, com uma modelagem que pode se aproximar da percepção visual humana para a geração de um método automático e preciso. Ocorre, entretanto, que os trabalhos apresentados até o momento sobre descritores fractais focam em métodos de estimativa de dimensão fractal mais conhecidos como Bouligand-Minkowski e Box-counting. Este projeto visa estudar mais a fundo o conceito, generalizando para outras abordagens de dimensão fractal, bem como explorando diferentes formas de se extraírem os descritores a partir da curva logarítmica associada à dimensão. Os métodos desenvolvidos são aplicados à análise de texturas, em problemas de classificação de bases públicas, cujos resultados podem ser comparados com métodos da literatura, bem como a segmentação de imagens de satélite e à identificação automática de amostras obtidas em estudos de nanotecnologia. Os resultados alcançados demonstram o potencial da metodologia desenvolvida para a solução destes problemas, mostrando tratar-se de uma nova fronteira a ser usada e explorada em análise de imagens e visão computacional como um todo. / This project describes the development, study and application of fractal descriptors to texture analysis. Recently, the literature has shown fractal geometry as a powerful tool for image analysis, with applications to several areas of science. Most of these works use fractal dimension as a descriptor of the object depicted in the image. However, due to the complexity of many problems in this context, some solutions have been proposed to improve this analysis. These proposed methods use not only the value of fractal dimension, but a set of measures which could be extracted by fractal geometry to describe the textures with greater richness and accuracy. Among such techniques, we emphasize the multifractal methodology, multiscale fractal dimension and, more recently, fractal descriptors. This latter technique has demonstrated to be efficient in solving problems related to the discrimination of texture and shape images. This is possible as the extracted descriptors provide a direct representation of the complexity (the details distribution along the scales of observation) in the image. Thus, this solution allows for a rich description of the image studied by analyzing the spatial/spectral distribution of pixels and intensity of colors/gray-levels, with a model which can approximate the human visual perception, generating an automatic and precise method. However, the works about fractal descriptors presented in the literature focus on classical methods to estimate fractal dimension, such as Bouligand-Minkowski and Box-counting. This project aims at studying more deeply the concept, generalizing to other approaches in fractal dimension, as well as exploring different ways of extracting the key features from the logarithmic curve associated with the dimension. The developed methods are applied to texture analysis, in classification problems over public databases, whose results can be compared with literature methods, as well as to the segmentation of satellite images and automatically identifying samples obtained from studies on nanotechnology. The results demonstrate the potential of the methodology developed to solve such problems, showing that this is a new frontier to be explored and used in image analysis and computer vision at all.

INTRODUÇÃO: A síndrome de Kabuki (SK) é uma desordem genética de etiologia desconhecida caracterizada por atraso mental moderado à severo, deficiência do crescimento pós-natal, e à face típica com fissuras palpebrais longas, eversão do terço lateral das pálpebras, orelhas proeminentes e ponte nasal larga e deprimida. Manifestações orais são comumente observadas em pacientes com SK e podem compreender: fissura lábiopalatina, úlvula bífida, maloclusão, atraso na erupção dentária, anomalias dentárias e cárie. CASUÍSTICA E MÉTODOS: Foram avaliados 9 pacientes com diagnóstico clínico de síndrome de Kabuki do Departamento de Genética do Instituto da Criança do Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo. Foram feitos exames clínicos odontológicos e avaliadas radiografias panorâmicas de face de todos os pacientes para coleta de dados. Como a maioria dos pacientes apresentou dentição mista ou permanente, a presença ou ausência de dentes na dentição decídua foi avaliada segundo a informação dada pelos pais ou responsáveis. RESULTADOS: Um paciente apresentou fissura palatina; três apresentaram cáries; sete tiveram ausências dentárias. Os dentes incisivos laterais superiores e os incisivos centrais inferiores foram os mais freqüentemente ausentes. Todos os dentes ausentes são permanentes, e não foi relatada nenhuma alteração na cronologia de erupção dental ou na morfologia dos dentes. Devido aos dentes ausentes, os pacientes apresentaram alteração, que poderia ser corrigida através de tratamento ortodôntico. Curiosamente, um paciente apresentou ausência de um canino superior, fato ainda não relatado na literatura sobre a SK até o momento. CONCLUSÕES: Os achados odontológicos contribuem para o diagnóstico clinico da síndrome de Kabuki, podendo contribuir como características adicionais nos casos de crianças com fenótipo com características leves / INTODUCTION: Kabuki syndrome (KS) is a genetic disorder of unknown etiology characterized by moderate to severe mental retardation, postnatal growth deficiency, and peculiar face with long palpebral fissures and eversion of the lateral third of the lower eyelids, prominent ears and broad and depressed nasal tip. Oral manifestations are commonly observed in KS and may comprise: cleft lip/palate, bifid tongue and uvula, malocclusion, delayed tooth eruption pattern, dental abnormalities and caries. METHODS: Were evaluated nine patients of the Department of Genetics (Instituto da Criança Hospital das Clínicas da Universidade de São Paulo) with clinical diagnosis of Kabuki syndrome. For data collection, were made clinical examinations and panoramic x-rays of all patients. Since most patients had mixed dentition, the presence or absence of primary teeth were assessed through the parents´ reports. RESULTS: One presented cleft palate; three presented caries; seven had missing teeth. Upper lateral incisors and inferior central incisors were the commonest absent teeth. All missing teeth are permanent, and there was no alteration of dental chronology or in morphology. Due to the absent teeth, patients present occlusal alteration, and they need orthodontic treatment. Curiously, one patient presented an absent upper canine, which was not reported in the literature up to now. CONCLUSIONS: Dental findings may be helpful for clinical diagnosis, or they may be an additional finding to substantiate the diagnosis of KS in children with mild phenotype

Descritores de características locais de imagens utilizados na representação de objetos têm se tornado muito populares nos últimos anos. Tais descritores têm a capacidade de caracterizar o conteúdo da imagem em dados compactos e discriminativos. As informações extraídas dos descritores são representadas por meio de vetores de características e são utilizados em várias aplicações, tais como reconhecimento de faces, cenas complexas e texturas. Neste trabalho foi explorada a análise e modelagem de descritores locais para caracterização de imagens invariantes a escala, rotação, iluminação e mudanças de ponto de vista. Esta tese apresenta três novos descritores locais que contribuem com o avanço das pesquisas atuais na área de visão computacional, desenvolvendo novos modelos para a caracterização de imagens e reconhecimento de imagens. A primeira contribuição desta tese é referente ao desenvolvimento de um descritor de imagens baseado no mapeamento das diferenças de nível de cinza, chamado Center-Symmetric Local Mapped Pattern (CS-LMP). O descritor proposto mostrou-se robusto a mudanças de escala, rotação, iluminação e mudanças parciais de ponto de vista, e foi comparado aos descritores Center-Symmetric Local Binary Pattern (CS-LBP) e Scale-Invariant Feature Transform (SIFT). A segunda contribuição é uma modificação do descritor CS-LMP, e foi denominada Modified Center-Symmetric Local Mapped Pattern (MCS-LMP). O descritor inclui o cálculo do pixel central na modelagem matemática, caracterizando melhor o conteúdo da mesma. O descritor proposto apresentou resultados superiores aos descritores CS-LMP, SIFT e LIOP na avaliação de reconhecimento de cenas complexas. A terceira contribuição é o desenvolvimento de um descritor de imagens chamado Mean-Local Mapped Pattern (M-LMP) que captura de modo mais fiel pequenas transições dos pixels na imagem, resultando em um número maior de \"matches\" corretos do que os descritores CS-LBP e SIFT. Além disso, foram realizados experimentos para classificação de objetos usando as base de imagens Caltech e Pascal VOC2006, apresentando melhores resultados comparando aos outros descritores em questão. Tal descritor foi proposto com a observação de que o descritor LBP pode gerar ruídos utilizando apenas a comparação dos vizinhos com o pixel central. O descritor M-LMP insere em sua modelagem matemática o cálculo da média dos pixels da vizinhança, com o objetivo de evitar ruídos e deixar as características mais robustas. Os descritores foram desenvolvidos de tal forma que seja possível uma redução de dimensionalidade de maneira simples e sem a necessidade de aplicação de técnicas como o PCA. Os resultados desse trabalho mostraram que os descritores propostos foram robustos na descrição das imagens, quantificando a similaridade entre as imagens por meio da abordagem Bag-of-Features (BoF), e com isso, apresentando resultados computacionais relevantes para a área de pesquisa. / Local feature descriptors used in objects representation have become very popular in recent years. Such descriptors have the ability to characterize the image content in compact and discriminative data. The information extracted from descriptors is represented by feature vectors and is used in various applications such as face recognition, complex scenes and textures. In this work we explored the analysis and modeling of local descriptors to characterize invariant scale images, rotation, changes in illumination and viewpoint. This thesis presents three new local descriptors that contribute to the current research advancement in computer vision area, developing new models for the characterization of images and image recognition. The first contribution is the development of a descriptor based on the mapping of gray-level-differences, called Center-Symmetric Local Mapped Pattern (CS-LMP). The proposed descriptor showed to be invariant to scale change, rotation, illumination and partial changes of viewpoint and compared to the descriptors Center-Symmetric Local Binary Pattern (CS-LBP) and Scale-Invariant Feature Trans- form (SIFT). The second contribution is a modification of the CS-LMP descriptor, which we call Modified Center-Symmetric Local Mapped Pattern (MCS-LMP). The descriptor includes the central pixel in mathematical modeling to better characterize the image content. The proposed descriptor presented superior results to CS-LMP , SIFT and LIOP descriptors in evaluating recognition of complex scenes. The third proposal includes the development of an image descriptor called Mean-Local Mapped Pattern (M-LMP) capturing more accurately small transitions of pixels in the image, resulting in a greater number of \"matches\" correct than CS-LBP and SIFT descriptors. In addition, experiments for classifying objects have been achieved by using the images based Caltech and Pascal VOC2006, presenting better results compared to other descriptors in question. This descriptor was proposed with the observation that the LBP descriptor can gene- rate noise using only the comparison of the neighbors to the central pixel. The M-LMP descriptor inserts in their mathematical modeling the averaging of the pixels of the neighborhood, in order to avoid noise and leave the more robust features. The results of this thesis showed that the proposed descriptors were robust in the description of the images, quantifying the similarity between images using the Bag-of-Features approach (BoF), and thus, presenting relevant computational results for the research area.

Visual Simultaneous Localization And Mapping (SLAM) allows for three dimensionalreconstruction from a camera’s output and simultaneous positioning of the camera withinthe reconstruction. With use cases ranging from autonomous vehicles to augmentedreality, the SLAM field has garnered interest both commercially and academically. A SLAM system performs odometry as it estimates the camera’s movement throughthe scene. The incremental estimation of odometry is not error free and exhibits driftover time with map inconsistencies as a result. Detecting the return to a previously seenplace, a loop, means that this new information regarding our position can be incorporatedto correct the trajectory retroactively. Loop detection can also facilitate relocalization ifthe system loses tracking due to e.g. heavy motion blur. This thesis proposes an odometric system making use of bundle adjustment within akeyframe based stereo SLAM application. This system is capable of detecting loops byutilizing the algorithm FAB-MAP. Two aspects of this system is evaluated, the odometryand the capability to relocate. Both of these are evaluated using the EuRoC MAV dataset,with an absolute trajectory RMS error ranging from 0.80 m to 1.70 m for the machinehall sequences. The capability to relocate is evaluated using a novel methodology that intuitively canbe interpreted. Results are given for different levels of strictness to encompass differentuse cases. The method makes use of reprojection of points seen in keyframes to definewhether a relocalization is possible or not. The system shows a capability to relocate inup to 85% of all cases when a keyframe exists that can project 90% of its points intothe current view. Errors in estimated poses were found to be correlated with the relativedistance, with errors less than 10 cm in 23% to 73% of all cases. The evaluation of the whole system is augmented with an evaluation of local imagedescriptors and pose estimation algorithms. The descriptor SIFT was found to performbest overall, but demanding to compute. BRISK was deemed the best alternative for afast yet accurate descriptor. Conclusions that can be drawn from this thesis is that FAB-MAP works well fordetecting loops as long as the addition of keyframes is handled appropriately.

Drug development is a long and expensive process. It is often not until potential drug candidates are administered to humans that accurate quantification of their pharmacokinetic characteristics is achieved. The goal of developing quantitative structure-pharmacokinetic relationships (QSPkRs) is to relate the molecular structure of a chemical entity with its pharmacokinetic characteristics. In this thesis artificial neural networks (ANNs) were used to construct in silico predictive QSPkRs for various pharmacokinetic parameters using different drug data sets. Drug pharmacokinetic data for all studies were taken from the literature. Information for model construction was extracted from drug molecular structure. Numerous theoretical descriptors were generated from drug structure ranging from simple constitutional and functional group counts to complex 3D quantum chemical numbers. Subsets of descriptors were selected which best modeled the target pharmacokinetic parameter(s). Using manual selective pruning, QSPkRs for physiological clearances, volumes of distribution, and fraction bound to plasma proteins were developed for a series of beta-adrenoceptor antagonists. All optimum ANN models had training and cross-validation correlations close to unity, while testing was performed with an independent set of compounds. In most cases the ANN models developed performed better than other published ANN models for the same drug data set. The ability of ANNs to develop QSPkRs with multiple target outputs was investigated for a series of cephalosporins. Multilayer perceptron ANN models were constructed for prediction of half life, volume of distribution, clearances (whole body and renal), fraction excreted in the urine, and fraction bound to plasma proteins. The optimum model was well able to differentiate compounds in a qualitative manner while quantitative predictions were mostly in agreement with observed literature values. The ability to make simultaneous predictions of important pharmacokinetic properties of a compound made this a valuable model. A radial-basis function ANN was employed to construct a quantitative structure-bioavailability relationship for a large, structurally diverse series of compounds. The optimum model contained descriptors encoding constitutional through to conformation dependent solubility characteristics. Prediction of bioavailability for the independent testing set were generally close to observed values. Furthermore, the optimum model provided a good qualitative tool for differentiating between drugs with either low or high experimental bioavailability. QSPkR models constructed with ANNs were compared with multilinear regression models. ANN models were shown to be more effective at selecting a suitable subset of descriptors to model a given pharmacokinetic parameter. They also gave more accurate predictions than multilinear regression equations. This thesis presents work which supports the use of ANNs in pharmacokinetic modeling. Successful QSPkRs were constructed using different combinations of theoretically-derived descriptors and model optimisation techniques. The results demonstrate that ANNs provide a valuable modeling tool that may be useful in drug discovery and development.

<p>This thesis is a part of a project where a new method, the base descriptor approach, is studied. The purpose of this method is to reduce drift and extract vital information from electronic tongue measurements. Reference solutions, called descriptors, are measured and the measurements are used to find base descriptors. A base descriptor is, in this thesis, a regression vector for prediction of the property that the descriptor represent. The property is in this case the concentration of a chemical substance in the descriptor solution. Measurements from test samples, in this case fruit juices, are projected onto the base descriptors to extract vital and drift-stable information from the test samples. </p><p>The base descriptors are used to determine the concentrations of the descriptors'chemical substances in the juices and thereby also to classify the different juices. It is assumed that the measurements of samples of juices and descriptors drift the same way. This assumption has to be true in order for the base descriptor approach to work. The base descriptors are calculated by multivariate regression methods like partial least squares regression (PLSR) and principal component regression (PCR). </p><p>Only two of the descriptors tested in this thesis worked as basis for base descriptors. The base descriptors'predictions of the concentrations of chemical substances in the juices are hard to evaluate since the true concentrations are unknown. Comparing the projections of juice measurements onto the base descriptors with a classification model on the juice measurements performed by principal component analysis (PCA), there is no significant difference in drift of the juice measurements in the results of the two methods. The base descriptors, however, separates the juices for classification somewhat better than the classification of juices performed by PCA.</p>

Shape description is an important problem in computer vision because most vision tasks that require comparing or matching visual entities rely on shape descriptors. In this thesis, two novel shape descriptors are proposed, namely Intersection Consistency Histogram (ICH) and Global Binary Patterns (GBP). The former is based on a local regularity measure called Intersection Consistency (IC), which determines whether edge pixels in an image patch point towards the center or not. The second method, called Global Binary Patterns, represents the shape in binary along horizontal, vertical, diagonal or principal directions. These two methods are extensively analyzed on several databases, and retrieval and running time performances are presented. Moreover, these methods are compared with methods such as Shape Context, Histograms of Oriented Gradients, Local Binary Patterns and Fourier Descriptors. We report that our descriptors perform comparable to these methods.

Aim: The primary aim of this study was to find if there is any correlation between the corneal radius of curvature and its eccentricity. Method: 45 subjects participated in this study, 24 emmetropes, 18 myopes and three hyperopes. All subjects were free of ocular abnormalities and had no media opacities. All the subjects had normal ocular health and good visual acuity of 1.0 or better for both distance and near. The values for eccentricity and corneal radius of curvature were obtained by using a Topcon CA-100F Corneal Analyzer. Results: For the 4.5 mm zone the only significant correlation between corneal radius of curvature and eccentricity was obtained for the mean of the meridian (p = 0.007). On the other hand, we found no significant correlation for the average of two meridians or for meridian 1 and meridian 2 separately in the 8.0 mm zone. Conclusions: We found no correlation between the corneal radius of curvature and the eccentricity for both zones. In addition, no correlation could be found between the spherical equivalent of the refractive errors and the corneal eccentricity. The reason for not finding any significant correlation between the two entities could be due to factors such as smaller sample size and poor distribution of refractive errors in the sample. Moreover, there may be other factors that could influence the overall corneal shape like eye shape, axial length and corneal diameter, which was not evaluated in this study.