multi-channel morphological profiles for classification of hyperspectral images using support vector machines多通道形态资料,使用支持向量机的高光谱图像分类.pdfVIP

Sensors 2009, 9, 196-218; doi:10.3390/ OPEN ACCESS sensors ISSN 1424-8220 /journal/sensors Article Multi-Channel Morphological Profiles for Classification of Hyperspectral Images Using Support Vector Machines Javier Plaza, Antonio J. Plaza * and Cristina Barra Department of Technology of Computers and Communications, University of Extremadura / Escuela Politécnica de Cáceres, Avenida de la Universidad s/n, E-10071 Cáceres, Spain; E-Mails: jplaza@unex.es; crbaar@unex.es * Author to whom correspondence should be addressed; E-Mail: aplaza@unex.es; Tel.: +34-927-257195; Fax: +34-927-257203 Received: 11 December 2008; in revised form: 7 January 2009 / Accepted: 7 January 2009 / Published: 8 January 2009 Abstract: Hyperspectral imaging is a new remote sensing technique that generates hundreds of images, corresponding to different wavelength channels, for the same area on the surface of the Earth. Supervised classification of hyperspectral image data sets is a challenging problem due to the limited availability of training samples (which are very difficult and costly to obtain in practice) and the extremely high dimensionality of the data. In this paper, we explore the use of multi-channel morphological profiles for feature extraction prior to classification of remotely sensed hyperspectral data sets using support vector machines (SVMs). In order to introduce multi-channel morphologi