Ocular and Iris Recognition Baseline Algorithm

Due to its distinctiveness, the human eye is a popular biometric feature used to identity a person with high accuracy. The “Grand Challenge” in biometrics is to have an effective algorithm for subject verification or identification under a broad range of image and environmental conditions. As a response to the challenge, this paper presents baseline performance results derived from an enhanced version of VASIR (Video-based Automated System for Iris Recognition), as well as initial performance results based on a broader ocular recognition system. We describe the details of the VASIR procedure and demonstrate its superiority over the IrisBEE (Iris Biometric Evaluation Environment) baseline algorithm. We examine the relationship between VASIR performance and image quality scores. Finally, for less-constrained imaging conditions, we provide a comparison of iris and ocular recognition results.