A Comparison of Daubechies and Gabor Wavelets for Classification of MR Images

Abstract

In this paper we report our experience using different types of wavelets and different SVM kernel functions for classification of Magnetic Resonance Images to identify those showing symptoms of Alzheimer's Disease. We have developed a novel computational framework for extracting discriminative Gabor wavelet features from the images for classification using Support Vector Machines with various kernel functions. Experiments show that Gabor wavelets perform better than Daubechies wavelets in classification. Our method outperformed other popular approaches recently reported in the literature. 100% classification accuracy has been achieved.