Performance Comparison of Wavelet and Contourlet Frame Based Features for Improving Classif ication Accuracy in RemoteSensing

Performance Comparison of Wavelet and Contourlet Frame Based Features for Improving Classif ication Accuracy in RemoteSensing Images

Conventional classification algorithms makes the use of only multispectral information in remote sensing image classification. Wavelet provides spatial and spectral character-istics of a pixel along with its neighb ours and hence this can be utilized for an improved classification. The major disadvan-tage of wavelet transform is the non availability of spatial frequency f eatures i n its direct ional components. The contourlet transform based laplacian pyramid followed by di-rectional filter banks is an efficient way of extracting features in th e d irectional c omponents. In th is paper different contourlet frame based feature extraction techniques for re-mote sensing images are proposed. Principal component anal-ysis (PCA) method is used to reduce the number of features. Gaussian Kernel fuzzy C-means classifiers uses these features to improve the classification accuracy. Accuracy assessment based on field visit data and cluster validity measures are used to measure the accuracy of the classified data. The experimen-tal r esult s hows that the overall accuracy is improved to 1.73 % (for LISS-II), 1.81 % (for LISS-III) and 1.95 % (for LISS-IV) and the kappa coefficient is improved to 0.933 (for LISS-II), 0.0103 (for LISS-III) and 0.0214 (for LISS-IV) and also the cluster validity measures gives better results when compared to existing method