A new approach for iris localization based on an improved level set method

Abstract

In iris recognition systems, iris localization is a critical step which affects the further results definitively. Most of the traditional localization methods were time consuming and sensitive to noises. To solve the problems, we propose an algorithm which adopts a momentum based level set method to locate the pupil boundary. This method hasan advantage of decreasing the effect of local optima solutions and poor convergence dramatically, thus it could accurately describes the pupil boundary and decrease the influences of error parts. Experiment results show the iris localization under this method has a higher accuracy, and the inner iris boundary is much closer to the real one, localization results have been improved significantly.