DocumentCode :
805829
Title :
Toward an Optimal SVM Classification System for Hyperspectral Remote Sensing Images
Author :
Bazi, Yakoub ; Melgani, Farid
Author_Institution :
Dept. of Inf. & Commun. Technol., Trento Univ.
Volume :
44
Issue :
11
fYear :
2006
Firstpage :
3374
Lastpage :
3385
Abstract :
Recent remote sensing literature has shown that support vector machine (SVM) methods generally outperform traditional statistical and neural methods in classification problems involving hyperspectral images. However, there are still open issues that, if suitably addressed, could allow further improvement of their performances in terms of classification accuracy. Two especially critical issues are: 1) the determination of the most appropriate feature subspace where to carry out the classification task and 2) model selection. In this paper, these two issues are addressed through a classification system that optimizes the SVM classifier accuracy for this kind of imagery. This system is based on a genetic optimization framework formulated in such a way as to detect the best discriminative features without requiring the a priori setting of their number by the user and to estimate the best SVM parameters (i.e., regularization and kernel parameters) in a completely automatic way. For these purposes, it exploits fitness criteria intrinsically related to the generalization capabilities of SVM classifiers. In particular, two criteria are explored, namely: 1) the simple support vector count and 2) the radius margin bound. The effectiveness of the proposed classification system in general and of these two criteria in particular is assessed both by simulated and real experiments. In addition, a comparison with classification approaches based on three different feature selection methods is reported, i.e., the steepest ascent (SA) algorithm and two other methods explicitly developed for SVM classifiers, namely: 1) the recursive feature elimination technique and 2) the radius margin bound minimization method
Keywords :
feature extraction; genetic algorithms; geophysics computing; image classification; multidimensional signal processing; remote sensing; support vector machines; feature detection; feature selection; generalization bounds; genetic algorithms; genetic optimization framework; hyperspectral remote sensing images; optimal SVM classification; radius margin bound minimization; recursive feature elimination; simple support vector count; sparseness; support vector machine; Genetics; Hyperspectral imaging; Hyperspectral sensors; Kernel; Minimization methods; Remote sensing; Sensor phenomena and characterization; Spectroscopy; Support vector machine classification; Support vector machines; Feature detection; feature selection; generalization bounds; genetic algorithms (GAs); hyperspectral image classification; sparseness; support vector machines (SVMs);
fLanguage :
English
Journal_Title :
Geoscience and Remote Sensing, IEEE Transactions on
Publisher :
ieee
ISSN :
0196-2892
Type :
jour
DOI :
10.1109/TGRS.2006.880628
Filename :
1717732
Link To Document :
بازگشت