Symmetric hash functions for secure fingerprint biometric systems

Securing biometrics databases from being compromised is one of the most important challenges that must be overcome in order to demonstrate the viability of biometrics based authentication. In this paper we present a novel method of hashing fingerprint minutia and performing fingerprint identification in the hash space. Our approach uses a family of symmetric hash functions and does not depend on the location of the (usually unstable) singular points (core and delta). In fact, most approaches of hashing minutia and developing a cancellable system described in the literature assume the location of the singular points. Others assume a pre-alignment between the test and the stored fingerprint templates. These assumptions are unrealistic given that fingerprints are very often only partially captured by the commercially available sensors. The Equal Error Rate (EER) achieved by our system is about 3%. We also present the performance analysis of a hybrid system that has an EER of about 2...

• Type: Journal
• Year: 2007
• Where: PRL
• Authors: Sergey Tulyakov, Faisal Farooq, Praveer Mansukhani, Venu Govindaraju
• Keywords: Biometrics Databases, PRL 2007, Singular Points, fingerprint Minutia