Feature extraction using dual-tree complex wavelet transform and gray level co-occurrence matrix

This paper introduces a new feature extraction method for texture classification application. In the proposed method, dual-tree complex wavelet transform is first performed on the original image to obtain sub-images at six directions. After that gray level co-occurrence matrix of each sub-image is calculated and the corresponding statistical values are used to construct the final feature vector. The experimental results demonstrate that our proposed method has the property of robustness, and can achieve higher texture classification accuracy rate than the conventional methods.