A novel high performance iris and pupil localization method

Abstract

Iris detection is a computationally intensive task in the overall iris biometric processing. In this paper we proposed a technique to localize the iris and the pupil in eye images efficiently and accurately. This paper includes three stages: The first stage is related to finding the centre and radius of pupil. In this stage, the problem of pupil non-uniformity which may appear in some images is solved and the pupil is detected. In the second stage a new approach, based on circular arc search, is proposed to extract iris boundary. The last stage includes wavelet-based feature extraction and classifier design. Our approach has been applied on the CASIA standard database. High accuracy of the proposed iris localization method resulted in a high performance iris recognition system.