Comparison Studies on Classification for Remote Sensing Image Based on Data Mining Method

Data mining methods have been widely applied on the area of remote sensing classification in recent years. In these methods, neural network, rough sets and support vector machine (SVM) have received more and more attentions. Although all of them have great advantages on dealing with imprecise and incomplete data, there exists essential difference among them. Until now, researches of these three methods have been introduced in lots of literatures but how to combine these theories with the application of remote sensing is an important tendency in the later research. However, all of them have their own advantage and disadvantage. To reveal their different characters on application of remote sensing classification, neural network, rough sets and support vector machine are applied to the area of remote sensing image classification respectively. Comparison result among these three methods will be helpful for the studies on emote sensing image classification. And also the paper provides us a new viewpoint on remote sensing image classification in the future work. Key-Words: remote sensing image classification, data mining, neural network, variable precision rough sets model, support vector machine, comparison studies