Experiments with an Improved Iris Segmentation Algorithm
AUTOID '05 Proceedings of the Fourth IEEE Workshop on Automatic Identification Advanced Technologies
Image understanding for iris biometrics: A survey
Computer Vision and Image Understanding
New Methods in Iris Recognition
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
IEEE Transactions on Circuits and Systems for Video Technology
Degradation of iris recognition performance due to non-cosmetic prescription contact lenses
Computer Vision and Image Understanding
Genetically identical irises have texture similarity that is not detected by iris biometrics
Computer Vision and Image Understanding
Hi-index | 0.00 |
Many iris recognition systems operate under the assumption that non-cosmetic contact lenses will not affect match quality and the convenience using iris biometrics. We show results opposing this belief with a study of 51 contact lens wearing subjects and 64 non contact lens wearing subjects. Our experimental results show that contacts lens wearers are 14 times more likely to be falsely rejected by the IrisBEE iris recognition system at a Hamming distance threshold of 0.32 than non contact lens wearers. We further classify contact lens wearers into four categories according to the type of lens and its visibility in the iris image. The false reject rate varies with different types of contacts and the artifacts they produce on iris images. This is the first work that we are aware of to look at the effects of prescription contact lenses on iris biometrics.