Topological multi-contour decomposition for image analysis and image retrieval
Contribuinte(s) |
UNIVERSIDADE DE SÃO PAULO |
---|---|
Data(s) |
20/10/2012
20/10/2012
2008
|
Resumo |
Successful classification, information retrieval and image analysis tools are intimately related with the quality of the features employed in the process. Pixel intensities, color, texture and shape are, generally, the basis from which most of the features are Computed and used in such fields. This papers presents a novel shape-based feature extraction approach where an image is decomposed into multiple contours, and further characterized by Fourier descriptors. Unlike traditional approaches we make use of topological knowledge to generate well-defined closed contours, which are efficient signatures for image retrieval. The method has been evaluated in the CBIR context and image analysis. The results have shown that the multi-contour decomposition, as opposed to a single shape information, introduced a significant improvement in the discrimination power. (c) 2008 Elsevier B.V. All rights reserved, |
Identificador |
PATTERN RECOGNITION LETTERS, v.29, n.11, p.1675-1683, 2008 0167-8655 http://producao.usp.br/handle/BDPI/28790 10.1016/j.patrec.2008.04.017 |
Idioma(s) |
eng |
Publicador |
ELSEVIER SCIENCE BV |
Relação |
Pattern Recognition Letters |
Direitos |
restrictedAccess Copyright ELSEVIER SCIENCE BV |
Palavras-Chave | #image analysis #image retrieval #topological control #pattern recognition #SEGMENTATION #NETWORKS #Computer Science, Artificial Intelligence |
Tipo |
article original article publishedVersion |