Home Itens selecionados Provedores de dados OAI Créditos Sobre Ajuda

			Busca avançada
	Provedor de dados ArchiMer (2) Autor Augustin, Jean-marie (2) Karoui, I (2) Boucher, J (1) Boucher, J.m. (1) Fablet, R (1) Fablet, Ronan (1) Pieczynski, W (1) Mais... Palavra-chave Active regions (1) Angular backscattering (1) Feature fusion and selection (1) Feature selection (1) Level sets (1) MMP (1) MRF based texture segmentation (1) Non parametric feature statistics (1) Segmentation (1) Sonar images (1) Texture (1) Texture recognition (1) Mais... Tipo do documento Text (2) Ano 2009 (1) 2008 (1) País France (2) Idioma Inglês (2)		Ordenar por:  Relevância Autor Título Ano Registros recuperados: 2 Primeira ... 1 ... Última Seabed segmentation using optimized statistics of sonar textures ArchiMer Karoui, I; Fablet, R; Boucher, J.m.; Augustin, Jean-marie. We propose and compare two supervised algorithms of the segmentation of textured sonar images with respect to seafloor types. We characterize sea-floors by a set of empirical distributions estimated on texture responses for a wide set of different filters with various parameterizations and we introduce a novel similarity measure between sonar textures in this feature space. Our similarity measure is defined as a weighted sum of Kullback-Leibler divergences between texture features. The weight setting is twofold. First each filter is weighted according to its discrimination power: the computation of these weights are issued from a margin maximization criterion. Second, an additional weight, evaluated as an angular distance between the incidence angles of... Tipo: Text Palavras-chave: Level sets; Active regions; MMP; Segmentation; Angular backscattering; Feature selection; Sonar images; Texture. Ano: 2009 URL: http://archimer.ifremer.fr/doc/2009/publication-6101.pdf Fusion of textural statistics using a similarity measure: application to texture recognition and segmentation ArchiMer Karoui, I; Fablet, Ronan; Boucher, J; Pieczynski, W; Augustin, Jean-marie. Features computed as statistics (e.g. histograms) of local filter responses have been reported as the most powerful descriptors for texture classification and segmentation. The selection of the filter banks remains however a crucial issue, as well as determining a relevant combination of these descriptors. To cope with selection and fusion issues, we propose a novel approach relying on the definition of the texture-based similarity measure as a weighted sum of the Kullback-Leibler measures between empirical feature statistics. Within a supervised framework, the weighting factors are estimated according to the maximization of a margin-based criterion. This weighting scheme can also be considered as a filter selection method: texture filter response... Tipo: Text Palavras-chave: MRF based texture segmentation; Texture recognition; Feature fusion and selection; Non parametric feature statistics. Ano: 2008 URL: http://archimer.ifremer.fr/doc/2008/publication-4546.pdf Registros recuperados: 2 Primeira ... 1 ... Última

Empresa Brasileira de Pesquisa Agropecuária - Embrapa Todos os direitos reservados, conforme Lei n° 9.610 Política de Privacidade Área restrita		Embrapa Parque Estação Biológica - PqEB s/n° Brasília, DF - Brasil - CEP 70770-901 Fone: (61) 3448-4433 - Fax: (61) 3448-4890 / 3448-4891 SAC: https://www.embrapa.br/fale-conosco