%0 Conference Proceedings
%4 dpi.inpe.br/sbsr@80/2008/11.17.10.14
%2 dpi.inpe.br/sbsr@80/2008/11.17.10.14.40
%@isbn 978-85-17-00044-7
%T Classificação Supervisionada de Imagens Texturais Utilizando Redes Neurais Artificiais
%D 2009
%A Leite, Emilson Pereira,
%A Souza Filho, Carlos Roberto de,
%@affiliation Instituto de Geociências - Universidade Estadual de Campinas
%@affiliation Instituto de Geociências - Universidade Estadual de Campinas
%@electronicmailaddress emilson@ige.unicamp.br
%@electronicmailaddress beto@ige.unicamp.br
%E Epiphanio, José Carlos Neves,
%E Galvão, Lênio Soares,
%B Simpósio Brasileiro de Sensoriamento Remoto, 14 (SBSR)
%C Natal
%8 25-30 abr. 2009
%I Instituto Nacional de Pesquisas Espaciais (INPE)
%J São José dos Campos
%P 7821-7828
%S Anais
%1 Instituto Nacional de Pesquisas Espaciais (INPE)
%K Semivariogramas, Classificação Supervisionada, Redes Neurais de Alimentação Direta, Imagens Texturais, Imagens de RADAR.
%X A methodology to perform supervised classification of textural images using Artificial Neural Networks for applications in the Geosciences is presented in this work. Feature vectors are built with textural information composed of semivariogram values, histogram measures of mean, standard deviation and weighted-rank fill ratio. Feed-forward back-propagation Artificial Neural Networks are designed and trained so as to minimize the mean squared error of the differences between feature and target vectors of training sets. At each training iteration, the mean squared error for validation and test sets are also evaluated. Global accuracy and kappa coefficient are calculated for training, validation and test sets, allowing a quantitative appraisal of the predictive power of the Neural Networks. The best model for classification of all pixels in a given textural image is obtained from a k-fold cross-validation. The methodology was tested using synthetic images and airborne, multi-polarized SAR imagery for geologic mapping, and the overall results are considered quite positive.
%9 Técnicas de Classificação e Mineração de Dados
%@language pt
%3 7821-7828.pdf