Comparison of Fuzzy Classifiers Based on Fuzzy Membership Functions : Applies to Satellite Landsat TM Image

  • Kim Jin Il (Department of Computer Engineering, Dongeui University) ;
  • Jeon Young Joan (Department of Computer Engineering, Dongeui University) ;
  • Choi Young Min (Department of Computer Engineering, Dongeui University)
  • Published : 2004.08.01

Abstract

The aim of this study is to compare the classification results for choosing the fuzzy membership function within fuzzy rules. There are various methods of extracting rules from training data in the process of fuzzy rules generation. Pattern distribution characteristics are considered to produce fuzzy rules. The accuracy of classification results are depended on not only considering the characteristics of fuzzy subspaces but also choosing the fuzzy membership functions. This paper shows how to produce various type of fuzzy rules from the partitioning the pattern spaces and results of land cover classification in satellite remote sensing images by adopting various fuzzy membership functions. The experiments of this study is applied to Landsat TM image and the results of classification are compared by fuzzy membership functions.

Keywords