Improved Masek approach for iris localization

Iris recognition technology has become famous in security applications because of its accuracy, safety and noninvasive biometric technologies. It demonstrates its efficiency as biometric-based authentication. This technology take advantages of random variations in the visible features of iris which is the colored part surrounding the pupil. Iris segmentation is the first and the key step at any iris recognition system. It directly affects the recognition rates. Divers methods have been suggested in the literature. Some of these methods assume iris by circle models, elliptic or none regularly form. The circle contour sampling parameter has been investigated to find a tradeoff between speed and accuracy [10] especially for embedded systems where real time aspect is a big challenge. Moreover most commercially systems today estimate iris region by circle. In this work we propose to enhance Masek algorithm which is circle model method. Our experimental results using CASIA iris database V3.0 illustrate significant improvement in the performance (30% in time computation and 4% in accuracy).