Multi-class Classification for Wuhan Area´s TM Image Based on Support Vector Machine

This paper proposes a multi-class classification method based on Support Vector Machine (SVM), with an emphasis on classes of Wuhan area´s water resources. First, this method builds a SVM model by selecting proper testing sample data of Wuhan area´s TM image. Then, the image is classified as 5 classes based on the algorithm of SVM model. The experimental results show that this method has obvious advantages in accuracy, compared with the traditional method-Maximum likelihood, especially on classes of water resources.