On Mixing Iris-Codes

Abstract

In a cancelable iris recognition technique, all enrollment patterns are masked using a transformation function, and the invertibility for obtaining the original data should not be possible. This paper presents an approach for mixing multi-biometric features based on Double Random Phase Encryption (DRPE) to obtain a single protected IrisCode from different IrisCodes based on the Fractional Fourier Transform (FrFT). For the IrisCode generation, two encryption keys (RPM1 and RPM2) are utilized. The RPM2 is suggested to be the right iris feature vector of the same user. As a result, this feature level mixing of two different templates highly increases privacy and slightly enhances performance compared to its original counterpart. This proposed system achieves a high success rate in identification due to the fact that the iris authentication issue has been transformed to a key authentication process.