Share Email Print

Proceedings Paper

Regularized methods for hyperspectral image classification
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In this paper, we analyze regularized non-linear methods in the context of hyperspectral image classification. For this purpose, we compare regularized radial basis function neural networks (Reg-RBFNN), standard support vector machines (SVM), and kernel Fisher discriminant (KFD) analysis both theoretically and experimentally. We focus on the accuracy of methods when working in noisy environments, high input dimension, and limited number of training samples. In addition, some other important issues are discussed, such as the sparsity of the solutions, the computational burden, and the capability of the methods to provide probabilistic outputs. Although in general all methods yielded satisfactory results, SVM revealed more effective than KFD and Reg-RBFNN in standard situations regarding accuracy, robustness, sparsity, and computational cost.

Paper Details

Date Published: 10 November 2004
PDF: 12 pages
Proc. SPIE 5573, Image and Signal Processing for Remote Sensing X, (10 November 2004); doi: 10.1117/12.601712
Show Author Affiliations
Gustavo Camps-Valls, Univ. de Valencia (Spain)
Lorenzo Bruzzone, Univ. degli Studi di Trento (Italy)

Published in SPIE Proceedings Vol. 5573:
Image and Signal Processing for Remote Sensing X
Lorenzo Bruzzone, Editor(s)

© SPIE. Terms of Use
Back to Top