Subpixel classifiers: fuzzy theory versus statistical learning algorithm

Anil Kumar; S. K. Ghosh; Vinay Kumar Dadhwal

doi:10.1117/1.2759178

1 June 2007 Subpixel classifiers: fuzzy theory versus statistical learning algorithm

Anil Kumar, S. K. Ghosh, Vinay Kumar Dadhwal

Author Affiliations +

Journal of Applied Remote Sensing, Vol. 1, Issue 1, 013517 (June 2007). https://doi.org/10.1117/1.2759178

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.

Citation Download Citation

Anil Kumar, S. K. Ghosh, and Vinay Kumar Dadhwal "Subpixel classifiers: fuzzy theory versus statistical learning algorithm," Journal of Applied Remote Sensing 1(1), 013517 (1 June 2007). https://doi.org/10.1117/1.2759178

Published: 1 June 2007

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available