Cancelable face using Chaos permutation

Biometric template protection is a vital issue in deploying a biometric recognition system. In this paper, a novel face template protection scheme based on Biohashing and permutation approach is proposed. In order to increase the template privacy and security, we propose a new version of Biohashing employing the Chaos map to permute feature vectors before providing secure templates. To evaluate the security and recognition accuracy of our proposed method, we tested our approach on ORL face database. Experimental results show that the proposed method keeps the recognition accuracy, while increasing the template security, privacy and cancelability, compared to the traditional Biohashing method.