摘要：In this study we investigate the performance of the Support Vector Machines SVM) classifier when applied to the classification of high dimensional remotely sensed image data. As SVM deals with a pair of classes at a time, we propose its implementation in a binary tree approach where two classes only are dealt with at each node. The accuracy of the thematic image produced by this classification scheme was evaluated for two different kernel functions and different data dimensionality. Tests were performed using hiperspectral image data collected by the sensor system AVIRIS. Results are presented and discussed.
其他摘要：In this study we investigate the performance of the Support Vector Machines SVM) classifier when applied to the classification of high dimensional remotely sensed image data. As SVM deals with a pair of classes at a time, we propose its implementation in a binary tree approach where two classes only are dealt with at each node. The accuracy of the thematic image produced by this classification scheme was evaluated for two different kernel functions and different data dimensionality. Tests were performed using hiperspectral image data collected by the sensor system AVIRIS. Results are presented and discussed.
关键词：Support Vector Machines;Classificador em Árvore Binária; Sensoriamento Remoto;Imagens Hiperespectrais.
