A protection scheme for enhancing biometric template security and discriminability

As biometric techniques are being used in a growing number of applications, biometric template security is becoming of great concern in biometric systems. Unlike passwords and tokens, compromised biometric templates cannot be revoked and reissued. In this paper we propose a biometric authentication system based on face recognition using 2D Discrete Cosine Transform and neural networks. A discriminability criterion is used to select the DCT coefficients that make up the biometric template and a user dependent pseudo-random ordering of the DCT template coefficients is applied to provide template security. Experimental results show how the application of such techniques leads to both, enhanced recognition performance and system security, because user authentication process merges biometric recognition with the knowledge of a secret key.