Share Email Print
cover

Proceedings Paper

A comparison of statistical and multiresolution texture features for improving hyperspectral image classification
Author(s): Vidya Manian; Luis O. Jimenez-Rodriguez; Miguel Velez-Reyes
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

This paper presents a method for combining both spectral and spatial features to perform hyperspectral image classification. Texture based spatial features computed from statistical, wavelet multiresolution, Fourier spectrum and Gabor filters are considered. A step wise feature selection method selects optimal set of features from the combined feature set. A comparison of the different spatial features for improving hyperspectral image classification is presented. The results show that wavelet based features and statistical features perform best. The effect of band subset selection using information based subset selection methods on the combined feature set is presented. Several results with hyperspectral images show the efficacy of utilizing spatial features.

Paper Details

Date Published: 19 October 2005
PDF: 11 pages
Proc. SPIE 5982, Image and Signal Processing for Remote Sensing XI, 59820I (19 October 2005); doi: 10.1117/12.627634
Show Author Affiliations
Vidya Manian, Univ. de Puerto Rico, Mayagüez (United States)
Luis O. Jimenez-Rodriguez, Univ. de Puerto Rico, Mayagüez (United States)
Miguel Velez-Reyes, Univ. de Puerto Rico, Mayagüez (United States)


Published in SPIE Proceedings Vol. 5982:
Image and Signal Processing for Remote Sensing XI
Lorenzo Bruzzone, Editor(s)

© SPIE. Terms of Use
Back to Top