Share Email Print
cover

Proceedings Paper

Wavelet-based dimension reduction for hyperspectral image classification
Author(s): Edward Howard Bosch; Jeng Eng Lin
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

For dimension reduction of hyperspectral imagery, we propose a modification to Principal Component Analysis (PCA), Karhunen-Loeve Transform, by choosing a set of basis vectors corresponding to the proposed transformation to be not only orthonormal but also wavelets. Although the eigenvectors of the covariance matrix of PCA minimize the mean square error over all other choices of orthonormal basis vectors, we will show that the proposed set of wavelet basis vectors have several desirable properties. After reducing the dimensionality of the data, we perform a supervised classification of the original and reduced data sets, compare the results, and assess the merits of such transformation.

Paper Details

Date Published: 23 September 2003
PDF: 13 pages
Proc. SPIE 5093, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery IX, (23 September 2003); doi: 10.1117/12.484876
Show Author Affiliations
Edward Howard Bosch, U.S. Army Topographic Engineering Ctr. (United States)
Jeng Eng Lin, George Mason Univ. (United States)


Published in SPIE Proceedings Vol. 5093:
Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery IX
Sylvia S. Shen; Paul E. Lewis, Editor(s)

© SPIE. Terms of Use
Back to Top