Identification of Band Reflectance and Land-cover Classification Using Fuzzy Linear Regression Analysis

This paper describes an application of the fuzzy linear regression analysis for land-cover classification of Landsat TM data. The reflectance of spectral bands for each land-cover class is considered as fuzzy numbers, and a fuzzy linear regression identification model and a fuzzy linear regression estimation model are established and their application results are discussed. The proposed method has a considerable advantage in application, being not limited by spatial resolution of remotely sensed data and making it possible to achieve higher accuracy with those remotely sensed data of lower spatial resolution.