Made available in DSpace on 2016-06-02T19:06:00Z (GMT). No. of bitstreams: 1 4756.pdf: 1515606 bytes, checksum: 12146689055c9826f258e527c3ae001a (MD5) Previous issue date: 2012-11-19 / Universidade Federal de Sao Carlos / This work proposes two new techniques of feature vector pre-processing to improve CBIR and image classification systems: a method of feature transformation based on the k-means clustering approach (Feature Transformation based on K-means - FTK) and a method of Weighted Feature Discretization - WFD. The FTK method employs the clustering principle of k-means to compact the feature vector space. The WFD method performs a weighted feature discretization, privileging the most important feature ranges to distinguish images. The proposed methods were employed to pre-process the feature vector in CBIR and in classification approaches, comparing the results with the pre-processing performed by PCA (a well known feature transformation method) and the original feature vector: FTK produced a reduction in the feature vector size with an improving in the query precision and a improvement in the classification accuracy; WFD improved the query precision up to and a improvement in the classification accuracy; the combination of WFD and FTK improved also the query precision and a improvement in the classification accuracy. These are very important results, especially when compared with PCA results, which leads to a minor reduction in the feature vector size, a minor increase in the query precision and a minor increase in the classification accuracy. Also the proposed approaches have linear computational cost where PCA has a cubic computational cost. The results indicate that the proposed approaches are well-suited to perform image feature vector pre-processing improving the overall quality of CBIR and classification systems. / Neste trabalho, propomos diminuir o gap semântico e os problemas de maldição de dimensionalidade apresentando duas técnicas de préprocessamento do vetor de características com o objetivo de melhorar a recuperação de imagens baseada em conteúdo e sistemas de classificação de imagens: um método de redução de dimensionalidade do vetor de características original, baseado no algoritmo k-means, chamado FTK (Feature Transformation based on K-means) e um método de discretização ponderada de características que privilegia as faixas de características mais importantes para distinguir imagens, chamado WFD (Weighted Feature Discretization). Os métodos propostos foram utilizados para pré-processar os vetores de características nas abordagens CBIR e classificação, comparando o pré-processamento executado pelo método PCA e os resultados dos vetores de características originais. O algoritmo FTK promoveu uma redução no tamanho do vetor de características com uma melhoria na precisão da consulta e na precisão de classificação. O algoritmo WFD melhorou a precisão da consulta e classificação; a combinação de dos dois algoritmos propostos também melhorou a precisão da consulta e classificação. Estes resultados são muito importantes, especialmente quando comparados com os resultados do método PCA, que também leva a uma redução no tamanho do vetor de características, a um menor aumento na precisão da consulta e a menor aumento na precisão da classificação. Além disso, as técnicas propostas têm custo computacional linear, enquanto o PCA tem um custo computacional cúbico. Os resultados indicam que os métodos propostos são abordagens adequadas para realizar pré-processamento dos vetores de características de imagens em sistemas CBIR e em sistemas de classificação.

Os sistemas de recuperação de imagens por conteúdo (CBIR -Content-based Image Retrieval) possuem a habilidade de retornar imagens utilizando como chave de busca outras imagens. Considerando uma imagem de consulta, o foco de um sistema CBIR é pesquisar no banco de dados as "n" imagens mais similares à imagem de consulta de acordo com um critério dado. Este trabalho de pesquisa foi direcionado na geração de vetores de características para um sistema CBIR considerando bancos de imagens médicas, para propiciar tal tipo de consulta. Um vetor de características é uma representação numérica sucinta 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 pode ser armazenada em uma base de dados, e assim, agilizar o processo de recuperação de imagens. Uma abordagem alternativa para caracterizar imagens para um sistema CBIR é a transformação do domínio. A principal vantagem de uma transformação é sua efetiva caracterização das propriedades locais da imagem. Recentemente, pesquisadores das áreas de matemática aplicada e de processamento de sinais desenvolveram técnicas práticas de "wavelet" para a representação multiescala e análise de sinais. Estas novas ferramentas diferenciam-se das tradicionais técnicas de Fourier pela forma de localizar a informação no plano tempo-freqüência; basicamente, elas têm a capacidade de mudar de uma resolução para outra, o que faz delas especialmente adequadas para a análise de sinais não estacionários. A transformada "wavelet" consiste de um conjunto de funções base que representa o sinal em diferentes bandas de freqüência, cada uma com resoluções distintas correspondentes a cada escala. Estas foram aplicadas com sucesso na compressão, melhoria, análise, classificação, caracterização e recuperação de imagens. Uma das áreas beneficiadas, onde essas propriedades têm encontrado grande relevância, é a área médica, através da representação e descrição de imagens médicas. Este trabalho descreve uma abordagem para um banco de imagens médicas, que é orientada à extração de características para um sistema CBIR baseada na decomposição multiresolução de "wavelets" utilizando os filtros de Daubechies e Gabor. Essas novas características de imagens foram também testadas utilizando uma estrutura de indexação métrica "Slim-tree". Assim, pode-se aumentar o alcance semântico do sistema cbPACS (Content-Based Picture Archiving and Comunication Systems), atualmente em desenvolvimento conjunto entre o Grupo de Bases de Dados e Imagens do ICMC--USP e o Centro de Ciências de Imagens e Física Médica do Hospital das Clínicas de Riberão Preto-USP. / Content-based image retrieval (CBIR) refers to the ability to retrieve images on the basis of the image content. Given a query image, the goal of a CBIR system is to search the database and return the "n" most similar (close) ones to the query image according to a given criteria. Our research addresses the generation of feature vectors of a CBIR system for medical image 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 CBIR 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 multiscale 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 one type of resolution for the other, which makes them especially suitable for the analysis of non-stationary signals. The "wavelet" transform is a set of basis functions that represents signals in different frequency bands, each one with a resolution matching its scale. They have been successfully applied to image compression, enhancements, analysis, classifications, characterization and retrieval. One privileged area of application where these properties have been found to be relevant is medical imaging. In this work we describe an approach to CBIR for medical image databases focused on feature extraction based on multiresolution "wavelets" decomposition, taking advantage of the Daubechies and Gabor. Fundamental to our approach is how images are characterized, such that the retrieval procedure can bring similar images within the domain of interest, using a metric structure indexing, like the "Slim-tree". Thus, it increased the semantic capability of the cbPACS(Content-Based Picture Archiving and Comunication Systems), currently in joined developing between the Database and Image Group of the ICMC--USP and the Science Center for Images and Physical Medic of the Clinics Hospital of Riberão Preto--USP.

In this master thesis is described how to design and implement classifier of defects detected during the final stage of production nonwovens. The beginning of the thesis is devoted to the analysis of options for image processing and classification. Followed by the part, where is described process of image segmentation and extraction of feature vector. Description of classifier implementation and table of achieved results of classification on real images of detected defects.

This thesis deals with extraction of data from cell images and their visualisation. Cell images are processed by FISH method. It discusses theory of diagnosis evaluation automation and cell features visualization. That concerns image processing, cell nuclei segmentation, feature extraction and data visualization.

There are billions of photos on the internet and as the size of these digital repositories grows, finding target picture becomes more and more difficult. To increase the informational quality of photo albums we propose a new method that selects representative pictures from a group of photographs using computer vision algorithms. The aim of this study is to analyze the issues about image features, image similarity, object clustering and examine the specific characteristics of photographs. Tests show that there is no universal image descriptor that can easily simulate the process of clustering performed by human vision. The thesis proposes a hybrid algorithm that combines the advantages of selected features together using a specialized multiple-step clustering algorithm. The key idea of the process is that the frequently photographed objects are more likely to be representative. Thus, with a random selection from the largest photo clusters certain representative photos are obtained. This selection is further enhanced on the basis of optimization, where photos with better photographic properties are being preferred.

To assist technology advancements, it is important to continue the search for new materials. The stability of a crystal structures is closely connected to its formation energy. By calculating the formation energies of theoretical crystal structures it is possible to find new stable materials. However, the number of possible structures are so many that traditional methods relying on quantum mechanics, such as Density Functional Theory (DFT), require too much computational time to be viable in such a project. A presented alternative to such calculations is machine learning. Machine learning is an umbrella term for algorithms that can use information gained from one set of data to predict properties of new, similar data. Feature vector representations (descriptors) are used to present data in an appropriate manner to the machine. Thus far, no combination of machine learning method and feature vector representation has been established as general and accurate enough to be of practical use for accelerating the phase diagram calculations necessary for predicting material stability. It is important that the method predicts all types of structures equally well, regardless of stability, composition, or geometrical structure. In this thesis, the performances of different feature vector representations were compared to each other. The machine learning method used was primarily Kernel Ridge Regression, implemented in Python. The training and validation were performed on two different datasets and subsets of these. The representation which consistently yielded the lowest cross-validated error was a representation using the Voronoi tessellation of the structure by Ward et. al. [Phys. Rev. B 96, 024104 (2017)]. Following up was an experimental representation called the SLATM representation presented by Huang and von Lilienfeld [arXiv:1707.04146], which is partially based on the Radial Distribution Function. The Voronoi representation achieved an MAE of 0.16 eV/atom at 3534 training set size for one of the sets, and 0.28 eV/atom at 10086 training set size for the other set. The effect of separating linear and non-linear energy contributions was evaluated using the sinusoidal and Coulomb representations. The result was that separating these improved the error for small training set sizes, but the effect diminishes as the training set size increases. The results from this thesis implicate that further work is still required for machine learning to be used effectively in the search for new materials.

Studien implementerade ett hjärna-dator-gränssnitt med hjälp av EEG-instrumentet MindWave Mobile Headset. Vi undersökte om det var möjligt att utföra fyra operationer genom att använda tankemönster. Fyra försökspersoner deltog i studien. Deras uppgift var att tänka i två tankemönster i följd som resulterade i en operation. EEG-signalen förbehandlas så att en mönsterigenkänningsmetod (k-NN) lättare kunde urskilja två tankemönster ur signalen. Denna undersökning har till vår vetskap inte tidigare utförts och är därmed kunskapsluckan vi ämnar fylla. Att fylla denna kunskapslucka är av intresse för bland annat användargrupperna: rörelsehindrade, spelintresserade och Virtual Reality-användare. Vi tog fram en modell som modellerade det bästa möjliga utfallet av metodiken i föreliggande studie. Undersökningens resultat kunde inte användas för att göra slutsatser angående frågeställningen då detta skulle vara att post hoc-teoretisera. I modellen visades dock tre av fyra operationer vara genomförbara, med en indikation om att även den fjärde var möjlig att utföra. Resultatet indikerar att det finns anledning att utföra en fortsatt studie. Den föreslagna fortsatta studien bör innefatta nya mätningar som testas av modellen för att fullt ut besvara problemformuleringen. / This study implements a Brain-Computer-Interface using the EEG-instrument MindWave Mobile Headset. We studied the feasibility of performing four operations using thought patterns. Four test subjects participated in the study. Their task was to think in two subsequent thought patterns that resulted in an operation. The EEG-signal was pre-processed in such a way that a pattern recognition algorithm (k-NN) more easily could recognize two thought patterns in the signal. This study has to our knowledge not been done before and thus aims to fill this lack of knowledge in the scientific community. User groups that have an interest in filling this gap are, amongst others; disabled people, gamers, and Virtual Reality users. We created a model that modeled the best possible outcome of the method used in this study. Conclusions drawn from the result can not be used to fully answer the problem statement, since it would be to post hoc-theorize. However, three out of four operations were possible to perform in the model, with an indication that the fourth also was possible to perform. These results indicate that there are grounds to continue this study. The proposed continued study should include new measurements that are tested by the model to determine if it is feasible to distinguish all four operations.

The task of detecting human faces within either a still image or a video frame is one of the most popular object detection problems. For the last twenty years researchers have shown great interest in this problem because it is an essential pre-processing stage for computing systems that process human faces as input data. Example applications include face recognition systems, vision systems for autonomous robots, human computer interaction systems (HCI), surveillance systems, biometric based authentication systems, video transmission and video compression systems, and content based image retrieval systems. In this thesis, non-traditional methods are investigated for detecting human faces within color images or video frames. The attempted methods are chosen such that the required computing power and memory consumption are adequate for real-time hardware implementation. First, a standard color image database is introduced in order to accomplish fair evaluation and benchmarking of face detection and skin segmentation approaches. Next, a new pre-processing scheme based on skin segmentation is presented to prepare the input image for feature extraction. The presented pre-processing scheme requires relatively low computing power and memory needs. Then, several feature extraction techniques are evaluated. This thesis introduces feature extraction based on Two Dimensional Discrete Cosine Transform (2D-DCT), Two Dimensional Discrete Wavelet Transform (2D-DWT), geometrical moment invariants, and edge detection. It also attempts to construct a hybrid feature vector by the fusion between 2D-DCT coefficients and edge information, as well as the fusion between 2D-DWT coefficients and geometrical moments. A self organizing map (SOM) based classifier is used within all the experiments to distinguish between facial and non-facial samples. Two strategies are tried to make the final decision from the output of a single SOM or multiple SOM. Finally, an FPGA based framework that implements the presented techniques, is presented as well as a partial implementation. Every presented technique has been evaluated consistently using the same dataset. The experiments show very promising results. The highest detection rate of 89.2% was obtained when using a fusion between DCT coefficients and edge information to construct the feature vector. A second highest rate of 88.7% was achieved by using a fusion between DWT coefficients and geometrical moments. Finally, a third highest rate of 85.2% was obtained by calculating the moments of edges. / Master of Science

Este trabalho foi desenvolvido com o intuito de se estabelecer uma metodologia para a classificação das cores de imagens digitais em cores perceptuais para se gerar um vetor de características que permita recuperar imagens através de seu conteúdo em uma base de dados. Em trabalhos e estudos correlatos analisados, as metodologias de agrupamento das diversas cores possíveis de uma imagem não permitem uma associação entre a cor digitalizada e a cor percebida por seres humanos. Estudos mostram que a maioria das culturas humanas associam às cores apenas onze termos: vermelho, amarelo, violeta, azul, verde, rosa, marrom, preto, branco, laranja e cinza. Este trabalho propõe, portanto, uma metodologia baseada em regras da lógica fuzzy, que permite associar a todas as possíveis cores de imagens digitais uma das onze cores culturais definidas, criando assim um histograma perceptual de cores. Isso permitiu a geração de um vetor de características para a recuperação de imagens baseada em conteúdo em uma base de dados. / This work aims at establishing a digital image classification methodology based on perceptual colors, by generating a feature vector that allows retrieving images from a database by their content. In related works the methodologies of grouping the diverse possible colors of an image do not allow associate digitized colors and those colors perceived by human beings. Studies show that the majority of human being culture associates only eleven terms to all the possible colors: red, yellow, blue, green, pink, brown, black, white, purple, orange and gray. This work purpose a methodology based on fuzzy logic that allows to associate the eleven cultural color terms with all of digitized colors by a perceptual color histogram. The image color quantization generates a feature vector used for content-based image retrieval. The results show that it is possible to use the perceptual color histogram for CBIR and in the semantic gap reduction.

No description available.