Iris Identification in 3D

Abstract

In the presence of eyelids and eyelashes movement, pupil dilation, poor lighting, blur due to movement during iris image acquisition, factors that collectively cause distortion in the iris image, 2D image-based iris identification techniques become limited and might lead to iris misclassification. To alleviate this problem, we introduce a novel 3D iris model and reader for iris identification. Using a set of at least two 2D images taken from different views, a small set of reliable and corresponding salient fiducial points (corner points taken from crypts, corona and serpentine rings of iris pattern) in the two images are extracted, from which a set of 3D iris salient points are constructed using triangulation. Corresponding salient points in the 2D images are found using the Random Sampling Consensus (RANSAC) algorithm, which is robust in identifying the inlier points that correspond to each other in the different views of the iris. From this small and reliable salient point set, a denser (high resolution) set of extra salient feature points is constructed at minimum cost using a loop sub-division method that yields corresponding extra salient points in the two images upon which a high-resolution 3D iris model is obtained. This 3D model construction method allows for a 3D distortion invariant classification of a test iris to one of many possible irises stored in the database.