Iris Perturbation Methods for Improved Recognition

Perturbations of software provided circular segmentations are used to generatemultiple probe templates from a single image. The multiple probes are matchedagainst a gallery in order to improve the verification rate of the original algorithm.Using too many of the generated probes will result in greatly increased runningtimes. As a result, various methods of finding and selecting perturbations to beused are empirically examined. Using ROC analysis of the true accept rate (TAR)at a given false accept rate of 0.001, many methods are discovered that performmuch better than the original algorithm, approximate the performance of usingevery perturbation to less than 0.2%, and require between 500 to 1000 times lesstime to verify a single image.