%0 Conference Proceedings
%4 sid.inpe.br/banon/2002/10.24.10.41
%2 sid.inpe.br/banon/2002/10.24.10.41.18
%@doi 10.1109/SIBGRA.2002.1167129
%T Texture feature neural classifier for remote sensing image retrieval systems
%D 2002
%A Martins, Mauricio Pozzobon,
%A Guimaraes, Lamartine N. Frutuoso,
%A Fonseca, Leila Maria Garcia,
%E Gonçalves, Luiz Marcos Garcia,
%E Musse, Soraia Raupp,
%E Comba, João Luiz Dihl,
%E Giraldi, Gilson,
%E Dreux, Marcelo,
%B Brazilian Symposium on Computer Graphics and Image Processing, 15 (SIBGRAPI)
%C Fortaleza, CE, Brazil
%8 10-10 Oct. 2002
%I IEEE Computer Society
%J Los Alamitos
%S Proceedings
%1 SBC - Brazilian Computer Society
%X Texture information is useful for image data browsing and retrieval. The goal of this paper is to present a texture classification system for remote sensing images addressed to the administration of great collections of those images. The proposed classifier is a hybrid system composed by an unsupervised neural network and a supervised one. Starting from a small portion of the image (pattern) the system should recognize the most similar class to the pattern in a database as well as to identify the images that contain similar patterns. The texture feature vectors used to characterize the patterns are obtained from the images processed by a bank of Gabor Filters. Some experimental results using textures of the Brodatz album, multi-spectral and radar images have presented here.
%@language en
%3 81.pdf
%O The conference was held in Fortaleza, CE, Brazil, from October 7 to 10.