Palm print biometric recognition based on Scattering Wavelet Transform

In this paper, we propose a Palm print biometric recognition system based on scattering wavelet transform. First a novel approach for extracting Region of Interest (ROI) from palm image is presented. Then, a Scattering Wavelet Transform (SWT) is used to extract discriminative features from the input images that are useful to enhance correct matching. Then, a simple Euclidean distance based matching metric is used to compare with the template database of SWT features. Simulation results show that excellent biometric recognition performance by features extracted from SWT and the performance does not degrade even if the input biometric images are subjected to various degrees of rotation and translation.