Two-Factor Cancelable Biometrics Authenticator

Biometrics-based authentication system offersadvantages of providing high reliability and accuracy. However, thecontemporary authentication system is impuissance to compromise. If abiometrics data is compromised, it cannot be replaced and renderedunusable. In this paper, a cancelable biometrics-based authenticator isproposed to solve this irrevocability issue. The proposed approach is atwo-factor authentication system, which requires both of the randomdata and facial feature in order to access the system. In this system,tokenized pseudo-random data is coupled with moment-based facialfeature via inner product algorithm. The output of the product is thendiscretized to generate a set of private binary code, coined as2factor-Hashing code, which is acted as verification key. If thisbiometrics-based verification key is compromised, a new one can beissued by replacing a different set of random number via tokenreplacement. Then, the compromised one is rendered completely useless.This feature offers an extra protection layer against biometricsfabrication since the verification code is replaceable. Experimentalresults demonstrate that the proposed system provides zero Equal ErrorRate in which there is a clear separation in between the genuine andthe imposter distribution populations.