A variant of cancelable iris biometric based on BioHashing

Abstract

As increasing demand for security of stored biometric data, cancelable biometric has attracted considerable attention. Cancelable biometric has advantages over other template protection methods because of diversity, revocability and non-invertibility. This paper introduces a cancelable iris biometric in which biometric features are combined with a tokenized (pseudo-) random number (TRN). The performance of the proposed cancelable iris biometric is evaluated comparing with that of the base BioHashing method at best, stolen-key and stolen-biometric scenarios. The experimentation of the proposed algorithm is carried out over the CASIA V1.0 and CASIA V3-Interval iris databases. The experimental results show that the proposed cancelable iris biometric outperforms base BioHashing method in terms of EER and FRR.