By Topic

Hyperspectral remote sensing image classification based on kernel fisher discriminant analysis

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Guo-Peng Yang ; Inst. of Surveying & Mapping, Zhengzhou ; Hang-Ye Liu ; Yu Xu-chu

Hyperspectral remote sensing technology combines the radiation information which relates to the targets' attribute and the space information which relates to the targets' position and shape. The spectrum information, which is enriched in the hyperspectral image, can facilitate the ground target classification, comparing with panchromatic remote sensing image and the multispectral remote sensing image. This paper introduced the classification method based on the kernel Fisher discriminant analysis, and then researched the selection methods of the kernel function and its parameter, and studied the decomposition methods on multi-classes classification methods. We selected the Gauss radial basic function and used the cross-validating grid search to find suitable parameters, to build an effective and robust multi-classes KFDA classifier. And then we applied this method to the hyperspectral remote sensing image classification, and the result showed that it has comparable classification accuracy in comparison to support vector machine, but the computation time is much less.

Published in:

Wavelet Analysis and Pattern Recognition, 2007. ICWAPR '07. International Conference on  (Volume:3 )

Date of Conference:

2-4 Nov. 2007