Combining Tasseled Cap Transformation with Support Vector Machine to classify Landsat TM imagery data

A supervised classification method combining Tasseled Cap Transformation (TCT) and Support Vector Machine (SVM) for Landsat TM imagery data is proposed in this paper. The spectral dimensionality of the imagery data is firstly reduced by TCT into the Brightness Component (TCTB) and Greenness Component (TCTG) and Wetness Component (TCTW), then the transformed data is inputted into Support Vector Machine and classified into water, wetland, shrub and grass land, farmland and town or bare land. The present results show that compared to SVM classification of the original six bands of Landsat TM imagery data, the classification method of combining TCT with SVM has a high accuracy.