Combinação de dispositivos de baixo custo para rastreamento de gestos

Pós-graduação em Ciência da Computação - IBILCE

Image segmentation through combined methods: watershed transform, unsupervised distance learning and normalized cut

Research on image processing has shown that combining segmentation methods may lead to a solid approach to extract semantic information from different sort of images. Within this context, the Normalized Cut (NCut) is usually used as a final partitioning tool for graphs modeled in some chosen method. This work explores the Watershed Transform as a modeling tool, using different criteria of the hierarchical Watershed to convert an image into an adjacency graph. The Watershed is combined with an unsupervised distance learning step that redistributes the graph weights and redefines the Similarity matrix, before the final segmentation step using NCut. Adopting the Berkeley Segmentation Data Set and Benchmark as a background, our goal is to compare the results obtained for this method with previous work to validate its performance.

Image segmentation using morphological watershed applied to cartography

Image segmentation is a process frequently used in several different areas including Cartography. Feature extraction is a very troublesome task, and successful results require more complex techniques and good quality data. The aims of this paper is to study Digital Image Processing techniques, with emphasis in Mathematical Morphology, to use Remote Sensing imagery, making image segmentation, using morphological operators, mainly the multi-scale morphological gradient operator. In the segmentation process, pre-processing operators of Mathematical Morphology were used, and the multi-scales gradient was implemented to create one of the images used as marker image. Orbital image of the Landsat satellite, sensor TM was used. The MATLAB software was used in the implementation of the routines. With the accomplishment of tests, the performance of the implemented operators was verified and carried through the analysis of the results. The extration of linear feature, using mathematical morphology techniques, can contribute in cartographic applications, as cartographic products updating. The comparison to the best result obtained was performed by means of the morphology with conventional techniques of features extraction. © Springer-Verlag 2004.

A graphical tool for the tomographic characterisation of microstructural features on metal matrix composites

Research on the micro-structural characterization of metal-matrix composites uses X-ray computed tomography to collect information about the interior features of the samples, in order to elucidate their exhibited properties. The tomographic raw data needs several steps of computational processing in order to eliminate noise and interference. Our experience with a program (Tritom) that handles these questions has shown that in some cases the processing steps take a very long time and that it is not easy for a Materials Science specialist to interact with Tritom in order to define the most adequate parameter values and the proper sequence of the available processing steps. For easing the use of Tritom, a system was built which addresses the aspects described before and that is based on the OpenDX visualization system. OpenDX visualization facilities constitute a great benefit to Tritom. The visual programming environment of OpenDX allows an easy definition of a sequence of processing steps thus fulfilling the requirement of an easy use by non-specialists on Computer Science. Also the possibility of incorporating external modules in a visual OpenDX program allows the researchers to tackle the aspect of reducing the long execution time of some processing steps. The longer processing steps of Tritom have been parallelized in two different types of hardware architectures (message-passing and shared-memory); the corresponding parallel programs can be easily incorporated in a sequence of processing steps defined in an OpenDX program. The benefits of our system are illustrated through an example where the tool is applied in the study of the sensitivity to crushing – and the implications thereof – of the reinforcements used in a functionally graded syntactic metallic foam.

Análise de formas planas em imagens digitais

Given the widespread use of computers, the visual pattern recognition task has been automated in order to address the huge amount of available digital images. Many applications use image processing techniques as well as feature extraction and visual pattern recognition algorithms in order to identify people, to make the disease diagnosis process easier, to classify objects, etc. based on digital images. Among the features that can be extracted and analyzed from images is the shape of objects or regions. In some cases, shape is the unique feature that can be extracted with a relatively high accuracy from the image. In this work we present some of most important shape analysis methods and compare their performance when applied on three well-known shape image databases. Finally, we propose the development of a new shape descriptor based on the Hough Transform.

A percepção visual visando a continuação gráfica na repetição modular do design de superfície

This article narrates from experiences in the classroom, the use of visual perception in the search for the solution of a basic problem of modular repetition, embodied by the lack of continuity in the elements that shape the design surface. Although Wong (1998) approach emphasizes the intuitive and intellectual approach as different parameters for building visual compositions, we list both as participants in the same focus, where the solution starts from the sensory stimulation.

Funções psicofísicas para área percebida, inferida e relembrada: o efeito da idade

O objetivo deste trabalho foi verificar o efeito da idade no expoente da função-potência nas Condições experimentais Perceptiva, Memória e Inferência. Para cada Condição, as faixas etárias dos sujeitos variaram de 17 a 34 anos (I), 38 a 57 anos (II) e 58 a 77 anos de idade (III). Os sujeitos estimaram áreas dos Estados do Brasil, utilizando o método psicofísico de estimação de magnitude. Os resultados obtidos pelas três Faixas etárias não diferiram para cada Condição experimental, com exceção da Condição Memória (24 horas). A análise entre as Condições experimentais e Faixas etárias evidenciou uma diferença da Condição Perceptiva em relação às demais, não havendo diferenças entre as Condições Memória e Inferência. Os dados apresentados sugerem que no processo de relembrar, não há perda da informação em função da idade.

Aprendizagem motora baseada em demonstrações de movimento biológico

O objetivo deste estudo foi avaliar o processo de aprendizagem motora de uma habilidade complexa da Ginástica Artística a partir da observação de demonstrações de modelos de pontos de luz e vídeo. Dezesseis participantes divididas em grupos dos respectivos modelos executaram um pré-teste, seguido de 100 tentativas de uma parada de mãos, igualmente distribuídas em blocos de 10 tentativas em dois dias, alternando períodos de demonstração e prática, com um teste de retenção após um dia. Cinemática de braço, tronco e perna das participantes possibilitaram análise da semelhança entre a coordenação de cada participante e do modelo e do tempo de movimento; a performance das participantes também foi avaliada por duas especialistas em Ginástica Artística. Ambas as análises indicaram que os grupos não diferiram. Os resultados são discutidos em termos da hipótese de suficiência de informação nos modelos de movimento biológico particularmente aplicada ao processo de aprendizagem de habilidades motoras complexas.

Modeling and analysis of artificial neural networks applied in operations research

Artificial neural networks are dynamic systems consisting of highly interconnected and parallel nonlinear processing elements. Systems based on artificial neural networks have high computational rates due to the use of a massive number of these computational elements. Neural networks with feedback connections provide a computing model capable of solving a rich class of optimization problems. In this paper, a modified Hopfield network is developed for solving problems related to operations research. The internal parameters of the network are obtained using the valid-subspace technique. Simulated examples are presented as an illustration of the proposed approach. Copyright (C) 2000 IFAC.

Comparison of fracture surface and plane section analysis for ceramic grain size characterisation

A method has been developed to obtain quantitative information about grain size and shape from fractured surfaces of ceramic materials. One elaborated a routine to split intergranular and transgranular grains facets of ceramic fracture surfaces by digital image processing. A commercial ceramic (ALCOA A-16, Al2O3-1.5% of CrO) was used to test the proposed method. Microstructural measurements of grain shape and size taken from fracture surfaces have been compared through descriptive statistics of distributions, with the corresponding measurements from polished and etched surfaces. The agreement between results, with the expected bias on grain size values from fractures, obtained for both types of surfaces allowed to infer that this new technique can be used to extract the relevant microstructural information from fractured surfaces, thus minimising the time consuming steps of sample preparation. (C) 2003 Elsevier Ltd. All rights reserved.

Fractal behavior throughout stretch zone of 15-5PH steel under elastic-plastic loading conditions

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

Avaliação quantitativa das dimensões óculo-palpebrais em portadores de cavidade anoftálmica em uso de prótese ocular externa

OBJETIVOS: Avaliar o posicionamento palpebral em portadores de cavidade anoftálmica com e sem prótese ocular externa, utilizando o processamento de imagem digital. MÉTODOS: Dezoito pacientes foram avaliados qualitativa e quantitativamente na Faculdade de Medicina de Botucatu - Universidade Estadual Paulista - UNESP, com e sem a prótese externa. Usando imagens obtidas por filmadora e processadas usando o programa Scion Image, mediu-se a altura do sulco palpebral superior, a altura da fenda palpebral e os ângulos palpebrais dos cantos interno e externo. RESULTADOS: Pseudo-estrabismo e sulco palpebral superior profundo foram as alterações mais freqüentes ao exame externo. Houve diferença significativa em todas as variáveis estudadas, com diminuição da altura do sulco palpebral superior, aumento da área da fenda palpebral e aumento dos ângulos palpebrais interno e externo quando o paciente estava usando a prótese externa. CONCLUSÃO: Todos os pacientes avaliados apresentaram algum tipo de anormalidade órbito-palpebral, o que reflete a dificuldade em se proporcionar ao portador de cavidade anoftálmica um aspecto idêntico ao que existe na órbita normal. O processamento de imagens digitais permitiu avaliação objetiva das dimensões óculo-palpebrais, o que poderá contribuir nas avaliações seqüenciais dos portadores de cavidade anoftálmica.

Dental students' knowledge of ergonomic postural requirements and their application during clinical care

Aim:To examine how much final-year undergraduate dental students know about postural dental ergonomic requirements, and how well they apply these requirements clinically.Background:Dentists are vulnerable to diverse mechanical (e.g. postural) and non-mechanical occupational risks.Materials and Methods:Eight postural requirements found in normalising documents were identified, reproduced, photographed, and analysed to develop a test of visual perception (TVP). Photographs of the 69 participating students were taken during their clinical care to ascertain ergonomics compliance, after which the students were administered the TVP. Pearson's test was used to correlate the level of knowledge (TVP) and its clinical application (photographic analysis) among the 552 observations made for each test (total of 1104 observations).Results:65.7% of the TVP questions were answered correctly and 35% of the photographic cases were in compliance with ergonomic requirements (+ 0.67, P < 0.0001).Conclusion:The knowledge of ergonomics postural requirements and their clinical application among the dental students surveyed were not satisfactory. The reasons for the learning difficulties encountered by the students should be identified to improve the learning process. The didactic use of digital images in this study may help in this endeavour.

Edge detection and noise removal by use of a partial differential equation with automatic selection of parameters

This work deals with noise removal by the use of an edge preserving method whose parameters are automatically estimated, for any application, by simply providing information about the standard deviation noise level we wish to eliminate. The desired noiseless image u(x), in a Partial Differential Equation based model, can be viewed as the solution of an evolutionary differential equation u t(x) = F(u xx, u x, u, x, t) which means that the true solution will be reached when t ® ¥. In practical applications we should stop the time ''t'' at some moment during this evolutionary process. This work presents a sufficient condition, related to time t and to the standard deviation s of the noise we desire to remove, which gives a constant T such that u(x, T) is a good approximation of u(x). The approach here focused on edge preservation during the noise elimination process as its main characteristic. The balance between edge points and interior points is carried out by a function g which depends on the initial noisy image u(x, t0), the standard deviation of the noise we want to eliminate and a constant k. The k parameter estimation is also presented in this work therefore making, the proposed model automatic. The model's feasibility and the choice of the optimal time scale is evident through out the various experimental results.

Classification and characterization of places for mapping of environment using hierarchical neural network and omnivision

Mobile robots need autonomy to fulfill their tasks. Such autonomy is related whith their capacity to explorer and to recognize their navigation environments. In this context, the present work considers techniques for the classification and extraction of features from images, using artificial neural networks. This images are used in the mapping and localization system of LACE (Automation and Evolutive Computing Laboratory) mobile robot. In this direction, the robot uses a sensorial system composed by ultrasound sensors and a catadioptric vision system equipped with a camera and a conical mirror. The mapping system is composed of three modules; two of them will be presented in this paper: the classifier and the characterizer modules. Results of these modules simulations are presented in this paper.