In this paper, we present the application to remote sensing SAR image classification of a new pattern recognition technique called Multi.calss Support Vector Machines (M-SVM). M-SVM are an extension of a new patter recognition technique recentli introduced within the framework of the Statistical Learning Theory developed by V. Vapnic and his co-workers, namely, the Support Vector Machines (SVM). Since SVM are properly binary classifiers, M-SVM is an eextension of SVM in order to apply the Vapnik theory also to patter recognitions in which there are involved more than two classes of elements. In this article we use the M-SVMs in order to classify a SAR image. The proposed algorithm returned interesting reuslts with respect to Neural Networks and Fuzzy classifiers, having a reliability factor around to 94%.
Titolo: | M-SVM SAR Images Classification: Experimental Results and Validations |
Autori: | |
Data di pubblicazione: | 2005 |
Rivista: | |
Handle: | http://hdl.handle.net/20.500.12318/4197 |
Appare nelle tipologie: | 1.1 Articolo in rivista |