Remote sensing data are frequently used to produce crisp and fuzzy classifications for land cover applications. Fuzzy approaches are attractive for classification of images dominated by mixed pixels. Recently, fully-fuzzy classification that can incorporate mixed pixels in all the three stages of a supervised classification has been recommended. In this Letter, the results of a case study on fully-fuzzy classification of Indian Remote Sensing (IRS) 1C Linear Imaging Self Scanning Sensor (LISS) III imagery are reported. The results illustrate that fully-fuzzy classification produces more accurate land-cover mapping than the conventional crisp classification. For instance, the areal extents of three dominant classes (i.e. agriculture, forest and grass) obtained from fully-fuzzy classification differ by only 13% from the actual areal extents, compared to 34% difference in area observed from crisp classification.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
Document Type: Research Article
School of Engineering and Applied Sciences, Aston University, Aston Triangle, Birmingham B4 7ET, UK
Department of Civil Engineering, Indian Institute of Technology Roorkee, Roorkee-247 667, Uttaranchal, India
Publication date: August 1, 2003
More about this publication?