%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2010/09.10.11.55
%2 sid.inpe.br/sibgrapi/2010/09.10.11.55.22
%@doi 10.1109/SIBGRAPI.2010.9
%T Distances Correlation for Re-Ranking in Content-Based Image Retrieval
%D 2010
%A Pedronette, Daniel Carlos Guimarães,
%A Torres, Ricardo da S.,
%@affiliation RECOD Lab - Institute of Computing - University of Campinas
%@affiliation RECOD Lab - Institute of Computing - University of Campinas
%E Bellon, Olga,
%E Esperança, Claudio,
%B Conference on Graphics, Patterns and Images, 23 (SIBGRAPI)
%C Gramado, RS, Brazil
%8 30 Aug.-3 Sep. 2010
%I IEEE Computer Society
%J Los Alamitos
%S Proceedings
%K content-based image retrieval, re-ranking, distance optimization, clustering.
%X Content-based image retrieval relies on the use of efficient and effective image descriptors. One of the most important components of an image descriptor is concerned with the distance function used to measure how similar two images are. This paper presents a clustering approach based on distances correlation for computing the similarity among images. Conducted experiments involving shape, color, and texture descriptors demonstrate the effectiveness of our method.
%@language en
%3 SIBGRAPFinal_PDFExpress.pdf