Share Email Print

Journal of Applied Remote Sensing

Subpixel classifiers: fuzzy theory versus statistical learning algorithm
Author(s): Anil Kumar; S. K. Ghosh; Vinay Kumar Dadhwal
Format Member Price Non-Member Price
PDF $20.00 $25.00
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

A comparative study between two approaches of subpixel classification, based on fuzzy set theory and statistical learning has been carried out. The fuzzy set classifiers investigated in this study are Fuzzy c-Means (FCM) and Possibilistic c-Means (PCM) in supervised modes. Further, Support Vector Machines (SVMs) have been used in this study for density estimation as a statistical learning subpixel classifier and Mean Field (MF) method has been used for easy and efficient learning procedure for the SVM. The three algorithms FCM, PCM and SVMs were evaluated in subpixel classification mode and accuracy assessment has been carried out using Fuzzy Error Matrix (FERM). Test on the two sub sets of LISS-III multi-spectral image from Resourcesat -1, (IRS-P6) satellite, indicates that density estimation based on SVM approach is consistent with different data sets and out performs both FCM as well as PCM approach.

Paper Details

Date Published: 1 June 2007
PDF: 14 pages
J. Appl. Rem. Sens. 1(1) 013517 doi: 10.1117/1.2759178
Published in: Journal of Applied Remote Sensing Volume 1, Issue 1
Show Author Affiliations
Anil Kumar, Indian Institute of Remote Sensing (India)
S. K. Ghosh, Indian Institute of Technology Roorkee (India)
Vinay Kumar Dadhwal, Indian Institute of Remote Sensing (India)

© SPIE. Terms of Use
Back to Top