Study On Classification Of Mixed Pixel Of Remote Sensing Image Based On Fuzzy Theory

Classification of mixed pixel is the difficult point of remote sensing image . Fuzzy theory is the effective method of classification of mixed pixel. It can get kind result in classification of mixed pixel. This paper has carried on systematic theory analysis and experiment to TM remote sensing image with the classification model of the fuzzy theory.1. The paper introduced the basic principle of the fuzzy theory. It applied to mixed pixel classification. ,and founded the classification model of fuzzy theory2. Collected endmember from the experiment image. Try to get endmember of the image through the experiment. Regard endmember as the cluster centre, carried on cluster's analysis, the ones that tried to get to all kinds of surface features like pixel were under the membership degree.3 used endmember to try to get to every classification surface feature like pixel were under the membership degree. According to the classification model of the fuzzy theory, Use MATLAB language to write the procedure, carry on the classification experiment.4 Compares the experimental result with the classification result of the greatest likelihood classification. The experimental result proves: Fuzzy theory classification method raise classification precision to mixed pixel , it is effective method for mixed pixel classification.