Title :
Support vector machines for classification of hyperspectral remote-sensing images
Author :
Melgani, Farid ; Bruzzone, Lorenzo
Author_Institution :
Dept. of Inf. & Commun. Technol., Trento Univ., Italy
Abstract :
In this paper, we address the problem of classification of hyperspectral remote-sensing images (in the original hyperdimensional feature space) by Support Vector Machines (SVMs). In particular, we investigate the effectiveness of SVMs in terms of classification accuracy, computational time and stability to parameter setting. Experiments, carried out on a standard AVIRIS hyperspectral data set, include a comparison with two other widely used nonparametric approaches, i.e., the K-nn and the Radial Basis Function (RBF) neural networks classifiers. The obtained results point out interesting properties of SVMs in hyperdimensional feature spaces and suggest them as a promising tool to classify hyperspectral remote-sensing images.
Keywords :
geophysical signal processing; geophysical techniques; geophysics computing; image classification; multidimensional signal processing; neural nets; radial basis function networks; remote sensing; terrain mapping; AVIRIS; IR; K-nn; SVM; accuracy; computational time; geophysical measurement technique; geophysics computing; hyperdimensional feature space; hyperspectral remote sensing; image classification; infrared; land surface; parameter setting; radial basis function; support vector machine; terrain mapping; visible; Communications technology; Cost function; Hyperspectral imaging; Lagrangian functions; Pattern recognition; Quadratic programming; Remote sensing; Shape control; Support vector machine classification; Support vector machines;
Conference_Titel :
Geoscience and Remote Sensing Symposium, 2002. IGARSS '02. 2002 IEEE International
Print_ISBN :
0-7803-7536-X
DOI :
10.1109/IGARSS.2002.1025088