A versatile iris segmentation algorithm

Abstract

In biometric authentication, iris recognition was shown to be one of the most accurate techniques. In unconstrained environment and capture conditions (e.g. with hand-held devices used outdoors), the iris image may be contaminated by noise and distortions which makes the iris segmentation and recognition process difficult. This paper presents a novel iris segmentation algorithm that addresses some of the issues raised by unconstrained iris recognition. There are two main contributions in the present work: first, the proposed segmentation algorithm is able to cope efficiently with both near infra red and visible spectrum images; second, the algorithm speed can be increased significantly with a minimal reduction in accuracy. The versatility of the algorithm has been tested using both near infrared iris images acquired with a hand-held device and colour iris images acquired in unconstrained environment.