Iris localization using mixture of gamma distributions in the segmentation process

Abstract

This paper contributes to more accurate iris segmentation. We propose a new approach for iris image segmentation based on mixture of Gamma distributions modeling and an extended Expectation Maximization (EM) algorithm. We apply our approach to segment iris images from the CASIA (Chinese Academy of Sciences Institute of Automation)-Iris-Twins testing database. The accuracy of our algorithm is proved based on Kullback Leibler distance computation.