Iris Verification Based On Iris Feature and Secret Pseudo-Random Number

An iris verification system based on the integration of secret pseudo-random number and the userspecific iris feature, which generated from the ID Log-Gabor filters, to produce a unique compact binary code per person is proposed in this paper. This dual factor authentication approach coined as S-Iris Ecoding has significant functional advantages over solely biometrics such as token replacement. In addition, the risk of security threats can be greatly reduced such as iris fabrication. Experimental results show that this method has good performance over traditional iris verification in which perfect verification rate of the genuine and imposter populations can be produced. By applying S-Iris Encoding, the original iris feature length is notably reduced to around 5% of the original size and a 0.0025% ≈ 0% of EER can be achieved.