Busca avançada
Ano de início
Entree


Object delineation by kappa-connected components

Texto completo
Autor(es):
Miranda, Paulo A. V. ; Falcao, Alexandre X. ; Rocha, Anderson ; Bergo, Felipe P. G.
Número total de Autores: 4
Tipo de documento: Artigo Científico
Fonte: EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING; v. N/A, p. 14-pg., 2008-01-01.
Resumo

The notion of "strength of connectedness" between pixels has been successfully used in image segmentation. We present extensions to these works, which can considerably improve the efficiency of object delineation tasks. A set of pixels is said to be a kappa-connected component with respect to a seed pixel, when the strength of connectedness of any pixel in that set with respect to the seed is higher than or equal to a threshold. We discuss two approaches that define objects based on kappa-connected components with respect to a given seed set: with and without competition among seeds. While the previous approaches either assume no competition with a single threshold for all seeds or eliminate the threshold for seed competition, we show that seeds with different thresholds can improve segmentation in both paradigms. We also propose automatic and user-friendly interactive methods to determining the thresholds. The proposed methods are presented in the framework of the image foresting transform, which naturally leads to efficient and correct graph algorithms. The improvements are demonstrated through several segmentation experiments involving medical images. Copyright (C) 2008 Paulo A. V. Miranda et al. (AU)

Processo FAPESP: 05/59808-0 - Segmentacao de imagens de ressonancia magnetica do cerebro humano.
Beneficiário:Paulo André Vechiatto de Miranda
Modalidade de apoio: Bolsas no Brasil - Doutorado
Processo FAPESP: 05/56578-4 - Centro multimodal de neuroimagens para estudos em epilepsia
Beneficiário:Fernando Cendes
Modalidade de apoio: Auxílio à Pesquisa - Programa CINAPCE - Temático
Processo FAPESP: 05/58103-3 - Classificadores e aprendizado em processamento de imagens e visão computacional
Beneficiário:Anderson de Rezende Rocha
Modalidade de apoio: Bolsas no Brasil - Doutorado
Processo FAPESP: 03/13424-1 - Identificação e caracterização das etiologias, mecanismos de lesão, disfunção neuronal e defeitos moleculares na epilepsia de lobo temporal mesial e sua relação com a resposta ao tratamento
Beneficiário:Iscia Teresinha Lopes Cendes
Modalidade de apoio: Auxílio à Pesquisa - Temático