Extended Averaged Learning Subspace Method for Hyperspectral Data Classification.docVIP

Sensors 2009, 9, 4247-4270; doi:10.3390/OPEN ACCESS sensors ISSN 1424-8220 /journal/sensors Article Extended Averaged Learning Subspace Method for Hyperspectral Data Classification Hasi Bagan 1,*, Wataru Takeuchi 2, Yoshiki Yamagata 1, Xiaohui Wang 3 and Yoshifumi Yasuoka 1 1 Center for Global Environmental Research, National Institute for Environmental Studies, 16-2 Onogawa, Tsukuba-City, Ibaraki, 305-8506, Japan; E-mails: hasi.bagan@nies.go.jp (H.B); yamagata@nies.go.jp (Y.Y.); yyasuoka@nies.go.jp (Y.Y.) 2 Institute of Industrial Science, University of Tokyo, Meguro-ku, Tokyo, 153-8505, Japan; E-mail: wataru@iis.u-tokyo.ac.jp (W.T.) 3 Department of Mathematics, University of Texas-Pan American, Edinburg, Texas 78539, USA; E-mail: xhwang@ (X.W.) * Author to whom correspondence should be addressed; E-Mail: hasi.bagan@nies.go.jp; Tel.: +81-29- 850-2567; Fax: +81-29-850-2960 Received: 14 May 2009; in revised form: 27 May 2009 / Accepted: 1 June 2009 / Published: 3 June 2009 Abstract: Averaged learning subspace methods (ALSM) have the advantage of being easily implemented and appear to outperform in classification problems of hyperspectral images. However, there remain some open and challenging problems, which if addressed, could further improve their performance in terms of classification accuracy. We carried out experiments mainly by using two kinds of improved subspace methods (namely, dynamic and fixed subspace methods), in conjunction with the [0,1] and [-1,+1] normalization methods. We used different performance indicators to support our experimental studies: classification accuracy, computation time, and the stability of the parameter settings. Results are presented for the AVIRIS Indian Pines data set. Experimental analysis showed that the fixed subspace method combined with the [0,1] normalization method yielded higher classification accuracy than other subspace methods. Moreover, AL