Detailed Analysis of IRIS Recognition Performance

Iris recognition is a well-known biometric identification system which distinguishes authentic and imposter individuals based on the features of their irides. It employs stringent statistical analyses of the features of irides due to the fact that each person has a unique iris, just like a fingerprint. In this work, the approach adopted towards the iris recognition problem is through an exhaustive and careful analysis of the statistical properties of the iris images and the randomness of spurious noise effects. The ability to differentiate two different templates from each other improves with the increase in the number of the degrees of freedom (DOF). The DOF depends on the encoding schemes utilized and moreover, it is hypothesized that the encoding schemes used in themselves could influence the recognition performance. The CASIA (Chinese Academy of Sciences Institute of Automation) version 1 database of iris images used in this study has been modified by the addition of artificial noise in order to simulate practical real life in situ noisy iris capture environments. The classical and state-of-the-art segmentation techniques have been compared, determining whether they are superior to the others under several conditions. The 1D, 2D Gabor filters and the short window implementation were all tested. The conclusion was that the 2D Gabor Filters produce a lower equal error rate (EER), higher accuracy and decidability than by using the one-dimensional log Gabor filter. After modifying the one-dimensional log Gabor filters, a lower EER and higher accuracy was found as the noise level increased. This makes the modified 1D log Gabor Filters a better proposition in noisy conditions. The generated iris templates have a predetermined theoretical value of DOF and from the statistical analysis, an experimental value can be determined. The relation between these values can be used as a metric to compare different databases.