Spectral Spatial Feature Based Classification of Hyperspectral Image Using Support Vector Machine

Now a days Support Vector Machine(SVM) has been used extensively in Hyperspectral Image(HSI) classification. It outperforms many classification algorithms and its performance still improving. Recently spectral-spatial information based algorithms are gaining more attention because of its robustness, accuracy and efficiency. In this paper, a SVM based classification method has been proposed which extracts features considering both spectral and spatial information. The proposed method exploits SVM to encode spectral-spatial inforamation of pixel as well as for classification task. The experiment has been performed using two benchmark datasets Indian Pines and Pavia University. Experiments show that the proposed method outperforms the classification algorithms K Nearest Neighbors(KNN), Linear Discriminant Analysis(LDA), Naive Bayes(NB) and Decision Tree.