Biometric Personal Identification based on Iris Patterns

This paper discusses an analysis of human iris patterns for recognition of biometric system which consists of a segmentation system that is based on the Hough transform, and is able to localize the circular iris and pupil region, occluding eyelids and eyelashes, and reflections. The extracted iris region is then normalized into a rectangular block with constant dimensions to account for imaging inconsistencies. To encode the unique pattern of the iris into a bit-wise biometric template, 1D Log-Gabor filter is used.Finally to match two iris templates hamming distance is used as matching metric. The system performance is analyzed on 312 iris images taken from standard CASIA Iris Interval database version 4. To establish the verification accuracy of iris representation and matching approach, each iris image in the database is matched with all the other iris images in the database and genuine and imposter distribution is found .The performance of the system is implemented by evaluating the Decidability Index (DI), False match rate (FMR), False Non-match rate (FNMR), Genuine Accept Rate (GAR) and Equal error rate (EER)