ISPRS, Vol.34, Part 2W2, “Dynamic and Multi-Dimensional GIS", Bangkok, May 23-25, 2001 
140 
cover itself in the test area that causes the result. The result of 
the test also indicates that the fully fuzzy classification method is 
very important because the classification result is not objective if 
the fuzziness is ignored in the process of training, classification 
or accuracy evaluation. Fortunately, the auxiliary decision of the 
geographical knowledge and information may strongly improve 
the accuracy of RS image classification and information 
extraction. At present, it has already used in so many studies. 
We will also consider its fuzziness while using it. 
REFERENCES 
1 Campbell J B. Introduction to Remote Sensing. New York: The 
Guilford Press, 1987 
2 Congalton R G. A Review of Assessing the Accuracy of 
Classification of Remotely Sensed Data. Remote Sensing of 
Environment, 1991,37(1): 35-46 
3 Foody G M. Fully Fuzzy Supervised Image Classification. In: 
Proceeding of RSS’95 Remote Sensing in Action, 1995. 
1187-1194 
4 Wang F. Improving Remote Sensing Image Analysis Through 
Fuzzy Information Representation. Photogrammetric 
Engineering and Remote Sensing, 1990, 56(8): 1163-1169 
5 Zhang J, Kirby R. P. An Elevation of Fuzzy Approaches to 
Mapping Land Cover from Aerial Photographs. ISPRS Journal 
of Photogrammetry and Remote Sensing, 1997(52): 193-201