Algoritmo SOM com estrutura hierárquica e dinâmica aplicado a compressão de imagens

ln this work the implementation of the SOM (Self Organizing Maps) algorithm or Kohonen neural network is presented in the form of hierarchical structures, applied to the compression of images. The main objective of this approach is to develop an Hierarchical SOM algorithm with static structure and another one with dynamic structure to generate codebooks (books of codes) in the process of the image Vector Quantization (VQ), reducing the time of processing and obtaining a good rate of compression of images with a minimum degradation of the quality in relation to the original image. Both self-organizing neural networks developed here, were denominated HSOM, for static case, and DHSOM, for the dynamic case. ln the first form, the hierarchical structure is previously defined and in the later this structure grows in an automatic way in agreement with heuristic rules that explore the data of the training group without use of external parameters. For the network, the heuristic mIes determine the dynamics of growth, the pruning of ramifications criteria, the flexibility and the size of children maps. The LBO (Linde-Buzo-Oray) algorithm or K-means, one ofthe more used algorithms to develop codebook for Vector Quantization, was used together with the algorithm of Kohonen in its basic form, that is, not hierarchical, as a reference to compare the performance of the algorithms here proposed. A performance analysis between the two hierarchical structures is also accomplished in this work. The efficiency of the proposed processing is verified by the reduction in the complexity computational compared to the traditional algorithms, as well as, through the quantitative analysis of the images reconstructed in function of the parameters: (PSNR) peak signal-to-noise ratio and (MSE) medium squared error

Correspondência estéreo usando imagens em multiresolução com profundidade variável

We propose a multi-resolution, coarse-to-fine approach for stereo matching, where the first matching happens at a different depth for each pixel. The proposed technique has the potential of attenuating several problems faced by the constant depth algorithm, making it possible to reduce the number of errors or the number of comparations needed to get equivalent results. Several experiments were performed to demonstrate the method efficiency, including comparison with the traditional plain correlation technique, where the multi-resolution matching with variable depth, proposed here, generated better results with a smaller processing time

Técnicas de computação natural para segmentação de imagens médicas

Image segmentation is one of the image processing problems that deserves special attention from the scientific community. This work studies unsupervised methods to clustering and pattern recognition applicable to medical image segmentation. Natural Computing based methods have shown very attractive in such tasks and are studied here as a way to verify it's applicability in medical image segmentation. This work treats to implement the following methods: GKA (Genetic K-means Algorithm), GFCMA (Genetic FCM Algorithm), PSOKA (PSO and K-means based Clustering Algorithm) and PSOFCM (PSO and FCM based Clustering Algorithm). Besides, as a way to evaluate the results given by the algorithms, clustering validity indexes are used as quantitative measure. Visual and qualitative evaluations are realized also, mainly using data given by the BrainWeb brain simulator as ground truth

Uma proposição para o cálculo de mapas de disparidade de imagens estéreo usando um interpolador neural baseado em funções de base radial

This study aims to seek a more viable alternative for the calculation of differences in images of stereo vision, using a factor that reduces heel the amount of points that are considered on the captured image, and a network neural-based radial basis functions to interpolate the results. The objective to be achieved is to produce an approximate picture of disparities using algorithms with low computational cost, unlike the classical algorithms

Posicionamento e movimentação de um robô humanóide utilizando imagens de uma câmera móvel externa

This work proposes a method to localize a simple humanoid robot, without embedded sensors, using images taken from an extern camera and image processing techniques. Once the robot is localized relative to the camera, supposing we know the position of the camera relative to the world, we can compute the position of the robot relative to the world. To make the camera move in the work space, we will use another mobile robot with wheels, which has a precise locating system, and will place the camera on it. Once the humanoid is localized in the work space, we can take the necessary actions to move it. Simultaneously, we will move the camera robot, so it will take good images of the humanoid. The mainly contributions of this work are: the idea of using another mobile robot to aid the navigation of a humanoid robot without and advanced embedded electronics; chosing of the intrinsic and extrinsic calibration methods appropriated to the task, especially in the real time part; and the collaborative algorithm of simultaneous navigation of the robots

SAMVC sistema de autoria de museus virtuais colaborativos

The use of graphical objects three-dimensional (3D) multimedia applications is gaining more space in the media. Networks with high transmission rates, computers with large processing and graphics boost and popularize such three-dimensional applications. The areas of 3D applications ranging from military applications, entertainment applications geared up for education. Within the applications related to education, we highlight the applications that create virtual copies of cultural spaces such as museums. Through this copy, you can virtually visit a museum, see other users, communicate, exchange information on works, etc. Thereby allowing the visit museums physically distant remote users. A major problem of such virtual environments is its update. By dealing with various media (text, images, sounds, and 3D models), its subsequent handling and update on a virtual environment requires staff with specialized knowledge. Speaking of museums, they hardly have people on your team with this profile. Inside the GT-MV (Grupo de Trabalho de Museus Virtuais), funded by RNP (Rede Nacional de Ensino e Pesquisa) propose a portal for registration, amendment and seen collaborative virtual museums of Brazil. The update, be it related to work or physical space, a system with a national scale like this, would be impossible if done only by the project team. Within this scenario, we propose the modeling and implementation of a tool that allows editing of virtual spaces in an easy and intuitive as compared with available tools. Within the context of GT-MV, we apply the SAMVC (Sistema de Autoria de Museus Virtuais Colaborativos) to museums where curators build the museum from a 3D floor plan (2D). The system, from these twodimensional information, recreates the equivalent in three dimensions. With this, through little or no training, team members from each museum may be responsible for updating the system

Sistema inteligente para detecção de manchas de óleo na superfície marinha através de imagens de SAR

Oil spill on the sea, accidental or not, generates enormous negative consequences for the affected area. The damages are ambient and economic, mainly with the proximity of these spots of preservation areas and/or coastal zones. The development of automatic techniques for identification of oil spots on the sea surface, captured through Radar images, assist in a complete monitoring of the oceans and seas. However spots of different origins can be visualized in this type of imaging, which is a very difficult task. The system proposed in this work, based on techniques of digital image processing and artificial neural network, has the objective to identify the analyzed spot and to discern between oil and other generating phenomena of spot. Tests in functional blocks that compose the proposed system allow the implementation of different algorithms, as well as its detailed and prompt analysis. The algorithms of digital image processing (speckle filtering and gradient), as well as classifier algorithms (Multilayer Perceptron, Radial Basis Function, Support Vector Machine and Committe Machine) are presented and commented.The final performance of the system, with different kind of classifiers, is presented by ROC curve. The true positive rates are considered agreed with the literature about oil slick detection through SAR images presents

Compressão Seletiva de Imagens Coloridas com Detecção Automática de Regiões de Interesse

There has been an increasing tendency on the use of selective image compression, since several applications make use of digital images and the loss of information in certain regions is not allowed in some cases. However, there are applications in which these images are captured and stored automatically making it impossible to the user to select the regions of interest to be compressed in a lossless manner. A possible solution for this matter would be the automatic selection of these regions, a very difficult problem to solve in general cases. Nevertheless, it is possible to use intelligent techniques to detect these regions in specific cases. This work proposes a selective color image compression method in which regions of interest, previously chosen, are compressed in a lossless manner. This method uses the wavelet transform to decorrelate the pixels of the image, competitive neural network to make a vectorial quantization, mathematical morphology, and Huffman adaptive coding. There are two options for automatic detection in addition to the manual one: a method of texture segmentation, in which the highest frequency texture is selected to be the region of interest, and a new face detection method where the region of the face will be lossless compressed. The results show that both can be successfully used with the compression method, giving the map of the region of interest as an input

Técnica de medição de área foliarconsumida por insetos através de digitalizador de imagens

Este trabalho teve por objetivo verificar a viabilidade do uso de digitalizador de imagens manual, acoplado a um microcomputador, para a avaliação do consumo de folhas de soja, por lagartas de 5o instar de Anticarsia gemmatalis Hübner (Lep.: Noctuidae), em comparação com o método de pesagem e do planímetro, baseando-se na eficiência dos métodos e no tempo gasto para a avaliação. Os testes foram realizados utilizando-se folhas de soja `IAC 8' e lagartas criadas em dieta artificial. Foram realizados 2 tipos de teste: 1o) oferecimento de folíolos inteiros de soja às lagartas e, 2o) oferecimento de disco de folhas de área conhecida. No 1o teste comparou-se o método de pesagem com o digitalizador de imagens (scanner); no 2o experimento foram comparados o método do planímetro com o digitalizador de imagens que emprega o programa PCXAREA. Os resultados obtidos demonstraram que não existem diferenças nas medições de folíolos e discos de soja consumidos por A. gemmatalis quando comparados os métodos tradicionais (planímetro e pesagem) e o de digitalização de imagens. A medição com o digitalizador reduziu o tempo de avaliação em 88,5% e 87%, em relação ao planímetro e método de pesagem, respectivamente, sendo plenamente viável a sua utilização.

Compósito reforçado com sisal para aplicação na moda

The objective of this research is the fabrication of a composite reinforced with dyed sisal fiber and polyester matrix for application in the fields such as, fashion, clothing, interior textiles; fashion accessories are some of the examples. For the fabrication of the composite, the sisal fibers were subjected to processes such as: chemical treatment with sodium hydroxide (NaOH) in the removal of impurities; bleaching for removing the yellowish color of the natural fiber and dyeing with direct dyes to confer the colors blue, green and orange. The search for new technologies ecologically correct has become a major concern in recent decades. Studies show that composite polymer reinforced by natural fibers is suitable for a large number of applications, and its use is advantageous in terms of economic and ecological. The dyed fibers were cut to a length of 30 mm, is used in the confection of webs. For this purpose, a web preparer by immersion, developed in the Laboratory of Chemical Textile of UFRN. The composite sheets measuring 300 x 300 x3 mm were molded by compression, with unsaturated orthophthalic polyester as matrix, and the samples in sizes 150 x 25 x 3 mm were cut with the aid of a laser machine, to be subjected to traction and flexion. The mechanical properties of traction and flexion in three points were performed in the Laboratory of metal and mechanical tests of Materials Engineering of UFRN. The resulting samples from the tests were evaluated in scanning electron microscope (SEM) at CTGas RN. On the basis of the analysis of the results from the mechanical tests, it was observed that the composite had good mechanical behavior, both in traction as in flexion. Furthermore, it was observed that in the water absorption test, the samples had a different percentage among themselves, this occurred due to the variation of density found in the fibre webs. The images of the SEM showed the failures from the manufacturing process and the adhesion of fibre/matrix. When the samples were prepared with the dyed fibers to be applied in fashion, the results were positive, and it can be concluded that the main objective of this work was achieved

Registro semiautomático entre imagens infravermelhas e RGB coletadas por um par de câmaras digitais

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Evolução e mapeamento do uso da terra, através de imagens aerofotogramétricas e orbitais em Santa Bárbara D'Oeste (SP)

Em Santa Bárbara D'Oeste,SP, foram realizados dois mapeamentos do uso da terra em área de 14.625 ha. No primeiro utilizou-se fotografias aéreas verticais pancromáticas (data de 25/6/78), na escala 1:35.000, e no segundo utilizou-se imagens orbitais do satélite LANDSAT-5 com sensor Thematic Mapper (data de 12/8/91), escala 1: 100.000, nas bandas 3, 4 e 5 e composição colorida 3/4/5. Para auxiliar a confecção desses mapas, obteve-se chaves de interpretação, tanto para as aerofotos como para as imagens orbitais. As fotografias aéreas proporcionaram um maior nível de detalhamento na identificação do uso da terra. A banda 3 e a composição colorida 3/4/5 foram as mais eficientes entre as imagens orbitais. Entre 1978 e 1991, a área de ocorrência de cana-de-açúcar permaneceu a mesma, as áreas de mata e pastagem diminuíram, enquanto que as áreas de reflorestamento e urbana aumentaram. Essa região teve sua capacidade de uso enquadrada, na maior parte, na classe IV: terras mais apropriadas para pastagens ou plantas perenes como a cana-de-açúcar, devendo-se aplicar técnicas intensivas de conservação, e com aptidão baseada em práticas agrícolas que refletem um alto nível tecnológico.

Aerofotos convencionais e imagens orbitais TM/LANDSAT no mapeamento morfopedológico em Santa Bárbara D'Oeste (SP)

Foram estudados, com o auxílio de fotografias aéreas, aspectos qualitativos e quantitativos do relevo e da rede de drenagem de solos de uma área de Santa Bárbara D'Oeste, SP. Esta região compreende 14.625 ha, onde foram selecionadas bacias hidrográficas de 3ª ordem de ramificação e amostras circulares de 5km². As unidades de mapeamento simples ou associações de solos são: Latossolo Vermelho Escuro, Podzólico, Litossolo + Podzólico, Terra Roxa Estruturada + Latossolo Roxo distrófico. Após a caracterização das feições fisiográficas, da área de ocorrência desses solos, foram realizados dois mapas morfopedológicos. No primeiro utilizou-se fotografias aéreas verticais pancromáticas na escala 1: 35.000 (data de 25/6/78) e no segundo imagens orbitais do sensor Thematic Mapper do LANDSAT-5, nas bandas 3, 4 e 5 e composição colorida 3/4/5 na escala 1: 100.000 (data de 12/9/91). As análises qualitativas e quantitativas do relevo (índice de declividade média) e rede de drenagem (densidade de drenagem, freqüência de rios, razão de textura) mostraram-se eficientes na diferenciação das unidades de solo estudadas, tanto em bacias hidrográficas como em amostras circulares. A utilização de fotografias aéreas, permitiu maior riqueza de detalhes na precisão dos limites das unidades de mapeamento e no maior número de unidades de mapeamento discriminadas em relação as imagens orbitais. A composição colorida 3/4/5 permitiu diferenciar os Latossolos argilosos dos Latossolos de textura média, assim como o Latossolo Húmico.

Caracterização espectral de áreas de gramíneas forrageiras infectadas com a doença mela-das-sementes da braquiária por meio de imagens CCD/CBERS-2

Imagens CCD/CBERS-2, nas bandas espectrais CCD2, CCD3 e CCD4, dos anos de 2004 e 2005, de Mirante do Paranapanema - SP, foram transformadas em reflectância de superfície usando o modelo 5S de correção atmosférica e normalizadas radiometricamente. O objetivo principal foi caracterizar espectralmente áreas de pastagens de Brachiaria brizantha em fase de florescimento, isentas e infectadas com a doença mela-das-sementes da braquiária, possibilitando a sua detecção por meio da comparação entre os valores de reflectância de superfície denominada de Fator de Reflectância Bidirecional de Superfície (FRBS). Teve-se, também, o objetivo de avaliar a eficácia das imagens CCD/CBERS-2 para a obtenção de respostas espectrais de pastagens. Os dosséis sadios e doentes da Brachiaria brizantha foram identificados por meio da análise dos valores de reflectância e dos dados observados no Índice de Estresse Hídrico Acumulativo Relativo da Cultura (ACWSI) obtidos na área de estudo. Os resultados indicaram que as principais diferenças foram a diminuição da reflectância na banda CCD3 e o aumento da reflectância na banda CCD4 nas áreas doentes. A metodologia empregada com o uso de dados do sensor CCD/CBERS-2, associados ao ACWSI, mostrou-se eficaz para discriminar dosséis infectados com a mela-das-sementes da braquiária.

Caracterização espectral da água do reservatório de Itupararanga, SP, a partir de imagens hiperespectrais hyperion e análise derivativa

The current accessibility to hyperspectral images of Hyperion/EO1 orbital sensor has brought new perspectives for studies of aquatic environments for allowing the remote estimative of several optically active constituents (OACs) in water body. The changes in the composition and concentration of OACs cause different patterns of absorption and scattering of electromagnetic radiation, likely to be detected using hyperspectral data. Therefore, an investigation was conducted taking into account the spectral characterization of water of a reservoir intended for public supply (Itupararanga Reservoir), from Hyperion/EO1 images and derivative analysis technique applied to spectral curves generated. Simultaneously to the acquisition of a Hyperion/EO1 image, a field campaign was carried out to collect limnological data in situ in georeferenced points. After radiometric correction of the image, reflectance curves of pixels were extracted for each station and the curves obtained were subjected to the technique of derivative analysis, which revealed features of absorption and scattering mainly associated to the presence of algal pigments. The results obtained show the presence of phytoplankton and algal activity, matching the field observation.