Hybrid frequency domain based feature extraction methods for human palm and face recognition

Abstract

Biometric plays a vital role in human authentication systems Unimodal and Multimodal biometrics have been an active research area for the past few decades In unimodal methods face and palmprint recognition are the challenging research fields Face recognition is investigated for different lighting conditions and different facial expressions Similarly palmprint recognition is investigated under various illuminations rotations and translations The research work on face and palmprint recognition systems has widely increased to improve the recognition rate and reduce execution time In order to improve recognition rate and reduce execution time various feature extraction feature selection and classification methods have been proposed The main objective of this research work is to develop a personal recognition system based on face palmprint and multimodal palmprint with high recognition rate and low execution time Feature extraction is the one of the important steps in biometrics newline