Edilberto Strauss

Dual-t-snakes model for medical imaging segmentation

The Dual-T-Snakes model plus dynamic programming (DP) techniques is a powerful methodology for boundary extraction and segmentation of 2D images. However, the original Dual-T-Snakes is not efficient for noisy images due to nonconvexity problems. In this paper we improve the model through multigrid and region growing methods to get more robustness against local minima. Besides, we demonstrate the advantage of using pass-band filtering methods and a fuzzy segmentation technique plus Dual-T-Snakes. We test these methods for artificial and cell images.

A boundary extraction method based on Dual-T-Snakes and dynamic programming

The original proposal of active contour models, also called snakes, for image segmentation, suffers from a strong sensitivity to its initial position and can not deal with topological changes. The sensitivity to initialization can be addressed by dynamic programming (DP) techniques which have the advantage of guaranteeing the global minimum and of being more stable numerically than the variational approaches. Their disadvantages are the storage requirements and computational complexity. In this paper we address these limitations of DP by reducing the region of interest (search space) through the use of the Dual-T-Snake approach. The solution of this method consists of two curves enclosing each object boundary which allows the definition of a more efficient search space for a DP technique. The resulting method (Dual-T-Snake plus DP) inherits the capability of changing the topology and avoiding local minima from the Dual-T-Snake and the global optimal properties of the dynamic programming. It can be also extended for 3D.

A semi-automatic surface reconstruction framework based on T-Surfaces and isosurface extraction methods

In this paper we present a new approach which integrates the T-surfaces model and isosurface generation methods in a general framework for surface reconstruction in 3D medical images. T-surfaces is a deformable model based on a triangulation of the image domain, a discrete surface model and an image threshold. Two types of isosurface generation methods are considered: the continuation ones and the marching ones. The former is useful during the reparameterization of T-surfaces while the later is suitable to initialize the model closer the boundary. Specifically, in a first stage, the T-surfaces grid and the threshold are used to define a coarser image resolution. This field is thresholded to get a 0-1 function which is processed by a marching method to generate polygonal surfaces whose interior may contain the desired objects. If a polygonal surface involves more than one object, then the resolution is increased in that region and the marching applied again. Next, we apply T-surfaces to improved the result. If the obtained topology remains incorrect, we enable the user to modify the topology by an interactive method based on the T-surfaces framework. Finally, we demonstrate the utility of diffusion methods for our approach.

A boundary extraction approach based on multi-resolution methods and the T-Snakes framework

We present a new approach which integrates the T-Snakes model and a multi-resolution method in a unified framework for segmentation and boundary extraction. In a first stage, a local scale property of the objects is used to define a triangulation of the image domain and a sampling (coarsest resolution) of the image field. The low resolution image is thresholded to get a 0-1 field which is processed by a simple continuation method to generate polygonal curves whose interior contain the desired objects. If the polygonal curve involves more than one object, then the resolution is increased in that region and the method will be applied again. This stage gives a rough approximation of the desired boundaries which will be improved by the T-Snakes to get the final result. We demonstrate the method for 2D medical imaging in the experimental results and indicate how it can be extended to 3D in future work.

Hugo against dengue: a serious game to educate people about dengue fever prevention

Owing to negligence and general lack of knowledge, dengue fever can spread if preventive measures are not adopted. This study employs a game to educate people about the causes of as well as the means to overcome the disease. It describes learning methodologies and specifies how games can assist in knowledge acquisition. Moreover, additional details are provided concerning the game engine chosen, supported platforms for implementation, and the prototypes operation requirements. Finally, a brief note is presented of future tasks involving a video game console based on the Android operating system and community centers focused on learning.

Computer theory and digital image processing applied to brain activation recognition

Human beings are constantly stimulated to activate mental operations associated with emotion. Moreover, there are different neural mechanisms that correspond to each emotion degrees. Science lacks knowledge on the operation of such mechanisms, despite being notorious that some regions are related to particular emotions. Modern studies generally enumerate the relationship , while it would be much more interesting if they explain the brain engine aspects. This article intends to present a technique for modeling human brain as a computable object by using Computer Theory and Digital Image Processing. A pattern cerebral activation recognizer automaton was constructed from functional magnetic resonance images in order to systemize the cerebral activation human process for a limited set of emotional stimulations.

Improving the original Dual-T-Snakes model

The dual-t-snakes model plus dynamic programming (DP) techniques is an efficient methodology for boundary extraction and segmentation of 2D images. However, the original proposal of the dual-t-snakes suffers from difficulties for parameters choice and instabilities due to the normal force definition. Also, the proposed method to push a snake way from a local minimum is not efficient for noise images. In this paper we address these limitations. Firstly, we reduce the number of parameters without affecting the basic features of dual-t-snakes. Next, we propose a new normal force definition which maintains the desired features of a balloon-like one but is more stable and gives better performance. Then, we propose other methods to avoid local minima based on mesh resolution, image statistics and a new region growing technique. We demonstrate these methods for artificial and cell images. Finally, in the future works, we figure out how to apply dual-t-snakes plus Viterbi together with non-parametric multiscale methods.

USO DE RECONHECIMENTO AUTOMÁTICO DE VOZ EM PORTUGUÊS DO BRASIL NA GERAÇÃO DE CLOSED CAPTION

Este artigo apresenta uma ferramenta desimulacao do modulador ISDB-TB, que permite realizaranalises complexas em cada estagio de processamento. Apartir de um arquivo Broadcast Transport Stream (BTS) epossivel acompanhar o processamento realizado em cadabloco do modulador ate o estagio final de transmissao.Utilizando um gerador de sinal vetorial e possivel realizartransmissoes reais com os arquivos de RF gerados nosimulador. Uma abordagem matematica e pratica sobre ofuncionamento de cada bloco que constitui o modulador erealizada iniciando pela descricao do sinal BTS ate oestagio final de transmissao.This article will explain some of the general ideas and specific techniques for usingambience in live broadcast audio that the author has developed over the past 30 years in thetelevision industry. The paper is concerned with stereo sound fields. The use of ambiencein a surround matrix is similar in approach, though it of course involves the perspective offront/back in addition to left/right.Este artigo apresenta medidas praticas da area de cobertura de uma emissora de televisao digital experimental da empresa Linear Equipamentos Eletronicos, operando em rede de frequencia unica (Single Frequency Network - SFN) na cidade de Santa Rita do Sapucai, Minas Gerais. O trabalho aborda aspectos teoricos de multiplos sinais resguardados por um prefixo ciclico, a utilizacao de distribuicao de conteudo por satelite, o emprego de enlaces terrestres na faixa de microondas para distribuicao de BTS e as particularidades em se empregar moduladores de diferentes fabricantes.Os receptores de TV Digital terrestre possuem umsoftware de sistema operacional que eventualmente necessita seratualizado pelo fabricante. Alem dos metodos tradicionais viaporta USB, internet, ou atraves das redes de servicos autorizados,surge a possibilidade desta atualizacao ser realizada pelo aratraves do proprio sinal digital que esta sendo recebido, sem anecessidade de intervencao do usuario. O sistema japones de TVDigital, onde o sistema brasileiro esta baseado tambem para aatualizacao de receptores via ar, possui uma entidadecentralizadora que e responsavel por controlar o conteudo detodos os fabricantes e envia-los aos receptores. No Brasil, por naoexistir tal entidade, criou-se um modelo de transmissao onde epossivel que cada emissora seja capaz de gerenciar seu proprioconteudo de download e envia-lo de acordo com o especificadopor cada fabricante. Este trabalho apresenta o estudo realizado,juntamente com o grupo de pesquisas da norma ABNT NBR15603 e os fabricantes de receptores, com a finalidade de definir aestrutura necessaria para cada radiodifusor, de forma a permitirque o envio de dados seja feito de maneira descentralizada e semque haja perdas para o usuario final.Este trabalho pretende continuar a discussao, em nivel teorico, desenvolvida no Congresso Set 2007, sobre o planejamento da grade de programacao em Televisao Digital Interativa. No atual cenario, os emissores tem o desafio de adequar as multiplas possibilidades de producao e distribuicao de conteudo da mais alta tecnologia, para um publico de cultura heterogenea e de contrastes sociais marcantes. Com a digitalizacao, a midia se transforma para alem da experiencia de assistir a uma programacao sequencial e se torna pervasiva, favorecendo, inclusive, o uso de recursos interativos em ambientes moveis e portateis. A televisao, enfim, adquire o status tecnologico que possibilita sua definitiva integracao ao ciberespaco, levando consigo, pela usabilidade, pelo entretenimento e pelo sentido de comunhao, a parcela da populacao que o computador, sozinho, nao alcanca. Contudo, a questao mais relevante, no processo de convergencia, esta na constituicao de uma grade que mantenha seu foco nas experiencias genuinamente televisivas. Aquelas que estimulam a interacao social, do publico entre si e com o assunto em pauta. O HDTV aumenta o prazer compartilhado de assistir televisao em casa. Os dispositivos moveis sao digitais e seus usuarios, interativos. Nesse cenario, tem muito a ganhar a programacao que souber conciliar a liberdade individual de escolhas com a satisfacao da experiencia comum, que primeiro estabelecer seus paradigmas “televisivos” de interacao com o publico.Com o advento do Sistema Brasileiro de TV Digital (SBTVD), e tendo em conta osseus recursos de universalizacao previstos no cronograma de implantacao, umagrande variedade de tecnologias de displays (incluindo receptores de altaresolucao, displays de celulares, etc.) ira requerer ensaios de resposta e defidedignidade colorimetrica para a adequada insercao no mercado brasileiro.Neste contexto, e importante destacar que a qualidade da resposta cromatica, naotica do telespectador, depende nao somente da adequacao dos parâmetros doSistema transmissor, mas tambem do desempenho dos displays (modernosdisplays planos ou Flat Panel Displays -FPD), dos efeitos de distorcoes em corproduzidas por nao linearidades nos set-top box e outros dispositivos detratamento de sinal de video.De uma maneira geral, a questao da fidelidade da resposta cromatica de displaysextrapola questoes ou elementos de apreciacao puramente subjetiva (qualidadeda resposta de um receptor de TV), assumindo cada vez mais relevância nomundo moderno a associacao das coordenadas de cor do elemento cromatico dodisplay a um dado mensurando: na area da saude, as cores apresentadas nosdisplays estao relacionadas a diagnosticos; no campo da ciencia, o espectrocromatico esta associado, cada vez de forma mais ampla, a novos mensurandos(altitude, temperatura, pressao, vazao, tipo de vegetacao, caracteristicasgeologicas, etc.).O objetivo deste trabalho e apresentar os testes a serem adotadas pelo CPqD eDIOPT/Inmetro no sentido de efetuar a caracterizacao de FPDs, em conformidadecom normas e recomendacoes internacionais e cadeias de rastreabilidadeenvolvidas.Este artigo apresenta um estudo de obras audiovisuais que utilizam a interatividade em sua narrativa, os chamados videos interativos, presentes na web e em DVD. Desenvolve uma discussao sobre as diferencas entre interacao e interatividade em videos interativos. Estabelece uma classificacao em modalidades das formas interativas em audiovisualEste trabalho pretende apresentar uma metodologia para mensuracao das degradacoes sofridas pelo sinal de video quando e transportado por redes IP....

NON-UNIFORM TERRAIN MESH SIMPLIFICATION USING ADAPTATIVE MERGE PROCEDURES

The performance of a walkthrough over terrain models is deeply influenced by the real scenario high level of details. To guarantee natural and smooth changes in a sequence of scenes, it is necessary to display the actual height field’s maps at interactive frame rates. These frame rates can be accomplished by reducing the number of rendered geometric primitives without compromising the visual quality. This paper describes an optimized algorithm for building a triangular mesh, the terrain model, which combines an efficient regular grid representation with low cost memory requirements, using a bottom-up approach.