Reconhecimento de padrões em imagens é uma área de grande interesse no mundo científico. Os chamados métodos de extração de características, possuem as habilidades de extrair características das imagens e também de reduzir a dimensionalidade dos dados gerando assim o chamado vetor de características. Considerando uma imagem de consulta, o foco de um sistema de reconhecimento de imagens de faces humanas é pesquisar em um banco de imagens, a imagem mais similar à imagem de consulta, de acordo com um critério dado. Este trabalho de pesquisa foi direcionado para a geração de vetores de características para um sistema de reconhecimento de imagens, considerando bancos de imagens de faces humanas, para propiciar tal tipo de consulta. Um vetor de características é uma representação numérica de uma imagem ou parte dela, descrevendo seus detalhes mais representativos. O vetor de características é um vetor n-dimensional contendo esses valores. Essa nova representação da imagem propicia vantagens ao processo de reconhecimento de imagens, pela redução da dimensionalidade dos dados. Uma abordagem alternativa para caracterizar imagens para um sistema de reconhecimento de imagens de faces humanas é a transformação do domínio. A principal vantagem de uma transformação é a sua efetiva caracterização das propriedades locais da imagem. As wavelets diferenciam-se das tradicionais técnicas de Fourier pela forma de localizar a informação no plano tempo-freqüência; basicamente, têm a capacidade de mudar de uma resolução para outra, o que as fazem especialmente adequadas para análise, representando o sinal em diferentes bandas de freqüências, cada uma com resoluções distintas correspondentes a cada escala. As wavelets foram aplicadas com sucesso na compressão, melhoria, análise, classificação, caracterização e recuperação de imagens. Uma das áreas beneficiadas onde essas propriedades tem encontrado grande relevância é a área de visão computacional, através da representação e descrição de imagens. Este trabalho descreve uma abordagem para o reconhecimento de imagens de faces humanas com a extração de características baseado na decomposição multiresolução de wavelets utilizando os filtros de Haar, Daubechies, Biorthogonal, Reverse Biorthogonal, Symlet, e Coiflet. Foram testadas em conjunto as técnicas PCA (Principal Component Analysis) e IMPCA (Image Principal Component Analysis), sendo que os melhores resultados foram obtidos utilizando a wavelet Biorthogonal com a técnica IMPCA / Image pattern recognition is an interesting area in the scientific world. The features extraction method refers to the ability to extract features from images, reduce the dimensionality and generates the features vector. Given a query image, the goal of a features extraction system is to search the database and return the most similar to the query image according to a given criteria. Our research addresses the generation of features vectors of a recognition image system for human faces databases. A feature vector is a numeric representation of an image or part of it over its representative aspects. The feature vector is a n-dimensional vector organizing such values. This new image representation can be stored into a database and allow a fast image retrieval. An alternative for image characterization for a human face recognition system is the domain transform. The principal advantage of a transform is its effective characterization for their local image properties. In the past few years researches in applied mathematics and signal processing have developed practical wavelet methods for the multi scale representation and analysis of signals. These new tools differ from the traditional Fourier techniques by the way in which they localize the information in the time-frequency plane; in particular, they are capable of trading on type of resolution for the other, which makes them especially suitable for the analysis of non-stationary signals. The wavelet transform is a set basis function that represents signals in different frequency bands, each one with a resolution matching its scale. They have been successfully applied to image compression, enhancement, analysis, classification, characterization and retrieval. One privileged area of application where these properties have been found to be relevant is computer vision, especially human faces imaging. In this work we describe an approach to image recognition for human face databases focused on feature extraction based on multiresolution wavelets decomposition, taking advantage of Biorthogonal, Reverse Biorthogonal, Symlet, Coiflet, Daubechies and Haar. They were tried in joint the techniques together the PCA (Principal Component Analysis) and IMPCA (Image Principal Component Analysis)

Stress detection based on non-EEG physiological data can be useful for monitoring drivers, pilots, and also for monitoring of people in ordinary situation, where standard EEG monitoring is unsuitable. This work uses Non-EEG database freely available from Physionet. The database contains records of heart rate, saturation of blood oxygen, motion, a conductance of skin and temperature recorded for 3 type of stress alternated with relax state. Two final models were created in this thesis. First model for Binary classification stress/relax, second for classification of 4 different type of psychical state. Best results were reached using model created by decision tree algorithm with 8 features for binary classification and with 8 features for classification of 4 psychical state. Accuracy of final models is aproximately 95 % for binary model and 99 % for classification of 4 psychical state. All algorithms were implemented in Python.

The biometric techniques are well known and widespread nowadays. In this context biometry means automated person recognition using anatomic features. This work uses the iris as the anatomic feature. Iris recognition is taken as the most promising technique of all because of its non-invasiveness and low error rate. The inventor of iris recognition is John G. Daugman. His work underlies almost all current public works of this technology. This final thesis is concerned with biometry based on iris images. The principles of biometric methods based on iris images are described in the first part. The first practical part of this work is aimed at the proposal and realization of two methods which localize the iris inner boundary. The third part presents the proposal and realization of iris image processing in order to classifying persons. The last chapter is focus on evaluation of experimental results and there are also compared our results with several well-known methods.

Biometrics is a method of recognizing the identity of a person based on unique biological characteristics that are unique to each person. The methods of biometric identification is currently becoming increasingly widespread in various sectors. This work is focused on the identification of a person by iris images. The introductory section describes the principles of the well-known methods for biometric applications and the next part describes the design method and its implementation in Matlab. In the practical part, fast radial symmetry method is used for detection of pupil, from which it derives further image processing. Two dimensional discrete welvet transform is used here. The proposed algorithm is tested on databases CASIA-Iris- Interval and database IITD.

[pt] Para o diagnóstico de distúrbios do sono, um dos exames mais usado é a polissonografia (PSG), na qual é registrada uma variedade de sinais fisiológicos. O exame de PSG é observado por um especialista do sono, processo que pode levar muito tempo e incorrer em erros de interpretação. O presente trabalho desenvolve e compara o desempenho de quatro sistemas baseados em arquiteturas de redes neurais de aprendizado profundo, mais especificamente, redes convolutivas (CNN) e redes recorrentes Long-Short Term Memory (LSTM), para a identificação de despertares relacionados ao esforço respiratório (Respiratory Effort-Related Arousal-RERA) e a eventos de despertar relacionados à apneia/hipopneia. Para o desenvolvimento desta pesquisa, foram usadas as informações de apenas seis canais eletroencefalográficos (EEG) provenientes de 994 registros de PSG noturna da base de dados PhysioNet CinC Challenge2018, além disso, foi considerado o uso de class weight e Focal Loss para lidar com o desbalanceamento de classes. Para a avaliação de cada um dos sistemas foram usadas a Accuracy, AUROC e AUPRC como métricas de desempenho. Os melhores resultados para o conjunto de teste foram obtidos com os modelos CNN1 obtendo-se uma Accuracy, AUROC e AUPRC de 0,8404, 0,8885 e 0,8141 respetivamente, e CNN2 obtendo-se uma Accuracy, AUROC e AUPRC de 0,8214, 0,8915 e 0,8097 respetivamente. Os resultados restantes confirmaram que as redes neurais de aprendizado profundo permitem lidar com dados temporais de EEG melhor que os algoritmos de aprendizado de máquina tradicional, e o uso de técnicas como class weight e Focal Loss melhoram o desempenho dos sistemas. / [en] For the diagnosis of sleep disorders, one of the most commonly used tests is polysomnography (PSG), in which a variety of physiological signs are recorded. The study of PSG is observed by a sleep therapist, This process may take a long time and may incur misinterpretation. This work develops and compares the performance of four classification systems based on deep learning neural networks, more specifically, convolutional neural networks (CNN) and recurrent networks Long-Short Term Memory (LSTM), for the identification of Respiratory Effort-Related Arousal (RERA) and to events related to apnea/hypopnea. For the development of this research, it was used the Electroencephalogram (EEG) data of six channels from 994 night polysomnography records from the database PhysioNet CinC Challenge2018, the use of class weight and Focal Loss was considered to deal with class unbalance. Accuracy, AUROC, and AUPRC were used as performance metrics for evaluating each system. The best results for the test set were obtained with the CNN1 models obtaining an accuracy, AUROC and AUPRC of 0.8404, 0.8885 and 0.8141 respectively, and RCNN2 obtaining an accuracy, AUROC and AUPRC of 0.8214, 0.8915 and 0.8097 respectively. The remaining results confirmed that deep learning neural networks allow dealing with EEG time data better than traditional machine learning algorithms, and the use of techniques such as class weight and Focal Loss improve system performance.

Ce mémoire de maîtrise présente une nouvelle approche non supervisée pour détecter et segmenter les régions urbaines dans les images hyperspectrales. La méthode proposée n ́ecessite trois étapes. Tout d’abord, afin de réduire le coût calculatoire de notre algorithme, une image couleur du contenu spectral est estimée. A cette fin, une étape de réduction de dimensionalité non-linéaire, basée sur deux critères complémentaires mais contradictoires de bonne visualisation; à savoir la précision et le contraste, est réalisée pour l’affichage couleur de chaque image hyperspectrale. Ensuite, pour discriminer les régions urbaines des régions non urbaines, la seconde étape consiste à extraire quelques caractéristiques discriminantes (et complémentaires) sur cette image hyperspectrale couleur. A cette fin, nous avons extrait une série de paramètres discriminants pour décrire les caractéristiques d’une zone urbaine, principalement composée d’objets manufacturés de formes simples g ́eométriques et régulières. Nous avons utilisé des caractéristiques texturales basées sur les niveaux de gris, la magnitude du gradient ou des paramètres issus de la matrice de co-occurrence combinés avec des caractéristiques structurelles basées sur l’orientation locale du gradient de l’image et la détection locale de segments de droites. Afin de réduire encore la complexité de calcul de notre approche et éviter le problème de la ”malédiction de la dimensionnalité” quand on décide de regrouper des données de dimensions élevées, nous avons décidé de classifier individuellement, dans la dernière étape, chaque caractéristique texturale ou structurelle avec une simple procédure de K-moyennes et ensuite de combiner ces segmentations grossières, obtenues à faible coût, avec un modèle efficace de fusion de cartes de segmentations. Les expérimentations données dans ce rapport montrent que cette stratégie est efficace visuellement et se compare favorablement aux autres méthodes de détection et segmentation de zones urbaines à partir d’images hyperspectrales. / This master’s thesis presents a new approach to urban area detection and segmentation in hyperspectral images. The proposed method relies on a three-step procedure. First, in order to decrease the computational complexity, an informative three-colour composite image, minimizing as much as possible the loss of information of the spectral content, is computed. To this end, a non-linear dimensionality reduction step, based on two complementary but contradictory criteria of good visualization, namely accuracy and contrast, is achieved for the colour display of each hyperspectral image. In order to discriminate between urban and non-urban areas, the second step consists of extracting some complementary and discriminant features on the resulting (three-band) colour hyperspectral image. To attain this goal, we have extracted a set of features relevant to the description of different aspects of urban areas, which are mainly composed of man-made objects with regular or simple geometrical shapes. We have used simple textural features based on grey-levels, gradient magnitude or grey-level co-occurence matrix statistical parameters combined with structural features based on gradient orientation, and straight segment detection. In order to also reduce the computational complexity and to avoid the so-called “curse of dimensionality” when clustering high-dimensional data, we decided, in the final third step, to classify each individual feature (by a simple K-means clustering procedure) and to combine these multiple low-cost and rough image segmentation results with an efficient fusion model of segmentation maps. The experiments reported in this report demonstrate that the proposed segmentation method is efficient in terms of visual evaluation and performs well compared to existing and automatic detection and segmentation methods of urban areas from hyperspectral images.

Ce mémoire de maîtrise présente une nouvelle approche non supervisée pour détecter et segmenter les régions urbaines dans les images hyperspectrales. La méthode proposée n ́ecessite trois étapes. Tout d’abord, afin de réduire le coût calculatoire de notre algorithme, une image couleur du contenu spectral est estimée. A cette fin, une étape de réduction de dimensionalité non-linéaire, basée sur deux critères complémentaires mais contradictoires de bonne visualisation; à savoir la précision et le contraste, est réalisée pour l’affichage couleur de chaque image hyperspectrale. Ensuite, pour discriminer les régions urbaines des régions non urbaines, la seconde étape consiste à extraire quelques caractéristiques discriminantes (et complémentaires) sur cette image hyperspectrale couleur. A cette fin, nous avons extrait une série de paramètres discriminants pour décrire les caractéristiques d’une zone urbaine, principalement composée d’objets manufacturés de formes simples g ́eométriques et régulières. Nous avons utilisé des caractéristiques texturales basées sur les niveaux de gris, la magnitude du gradient ou des paramètres issus de la matrice de co-occurrence combinés avec des caractéristiques structurelles basées sur l’orientation locale du gradient de l’image et la détection locale de segments de droites. Afin de réduire encore la complexité de calcul de notre approche et éviter le problème de la ”malédiction de la dimensionnalité” quand on décide de regrouper des données de dimensions élevées, nous avons décidé de classifier individuellement, dans la dernière étape, chaque caractéristique texturale ou structurelle avec une simple procédure de K-moyennes et ensuite de combiner ces segmentations grossières, obtenues à faible coût, avec un modèle efficace de fusion de cartes de segmentations. Les expérimentations données dans ce rapport montrent que cette stratégie est efficace visuellement et se compare favorablement aux autres méthodes de détection et segmentation de zones urbaines à partir d’images hyperspectrales. / This master’s thesis presents a new approach to urban area detection and segmentation in hyperspectral images. The proposed method relies on a three-step procedure. First, in order to decrease the computational complexity, an informative three-colour composite image, minimizing as much as possible the loss of information of the spectral content, is computed. To this end, a non-linear dimensionality reduction step, based on two complementary but contradictory criteria of good visualization, namely accuracy and contrast, is achieved for the colour display of each hyperspectral image. In order to discriminate between urban and non-urban areas, the second step consists of extracting some complementary and discriminant features on the resulting (three-band) colour hyperspectral image. To attain this goal, we have extracted a set of features relevant to the description of different aspects of urban areas, which are mainly composed of man-made objects with regular or simple geometrical shapes. We have used simple textural features based on grey-levels, gradient magnitude or grey-level co-occurence matrix statistical parameters combined with structural features based on gradient orientation, and straight segment detection. In order to also reduce the computational complexity and to avoid the so-called “curse of dimensionality” when clustering high-dimensional data, we decided, in the final third step, to classify each individual feature (by a simple K-means clustering procedure) and to combine these multiple low-cost and rough image segmentation results with an efficient fusion model of segmentation maps. The experiments reported in this report demonstrate that the proposed segmentation method is efficient in terms of visual evaluation and performs well compared to existing and automatic detection and segmentation methods of urban areas from hyperspectral images.

This thesis summarizes the information retrieval theory, the relational model basic and focuses on the data indexing in relational database systems. The thesis focuses on multimedia data searching. It includes description of automatic multimedia data content extraction and multimedia data indexing. Practical part discusses design and solution implementation for improving query effectivity for multidimensional vector similarity which describes multimedia data. Thesis final part discusses experiments with this solution.