Identity verification using iris biometrics is degraded if portions of the iris texture have a distorted appearance in the image. Distorted texture appearance can result from various causes, including contact lens artifacts, occlusion by hair, eyelids and eyelashes, and specular highlights. Previous work in iris biometrics attempts to cope with occlusion by eyelids / eyelashes and with specular highlights through improved segmentation of the iris region. Our approach assumes that some local distortions of the iris texture are not detected at the segmentation stage, and that these generate corresponding regions of local distortion in the iris code derived from the image. We introduce an approach to detect such regions of local distortion in the iris code through analysis of the iris code matching results. We know of no previous work that attempts to detect distortions of iris texture through analyzing the iris code matching results.
展开▼