A template privacy protection scheme for fingerprint minutiae descriptors

Abstract

It is important in biometric person recognition systems to protect personal data and privacy of users. This paper introduces a new mechanism to revoke and protect fingerprint minutiae information, which can be used in today's security-aware society. The recently developed minutiae cylinder code (MCC), which provides rotation and translation invariant descriptors for accurate fingerprint recognition by describing minutiae neighborhoods with respect to each other, is used as baseline fingerprint descriptor. A hybrid scheme combining a transformation and a user key is designed to provide the MCC-based fingerprint representation with revocability and irreversibility properties for template privacy protection across multiple applications. Furthermore, using the publicly available FVC datasets, it is demonstrated that the designed scheme improves the baseline accuracy of fingerprint recognition using the MCC method.