Fusing structure and color features for cancelable face recognition

Abstract

Face-based biometric recognition is widely used nowadays, where substantial face images are commonly stored on third-party servers. Since the sensitive information of an individual is contained in facial image such as the age and health condition, it is necessary to protect its privacy and security. This paper investigates a cancelable color face template protection algorithm. To make full use of quaternion representation, the structural information including local variance and gradient is respectively served as the real part. To achieve revocability and ability to redistribute, the strategy of random permutation with binary matrix is adopted. Afterwards, the quaternion-based two-dimensional principal component analysis is employed to extract features. With them, the extreme learning machine can be trained and used for recognition. Experimental results performed on four different color face datasets have demonstrated that the fusion of structural information can greatly improve the accuracy. More importantly, the random permutation not only does not reduce the recognition accuracy, but also guarantees the security and revocation of face template.