Enhancement segmentation technique for iris recognition system based on Daugman's Integro-differential operator

摘要

In spite of having been highly recognized as one of the critical steps in recognizing and determining the accuracy of iris matching, segmentation process of Iris is still encountered with few problematic challenges, especially in the process of separating the iris from the eye image and eyelids and eyelashes as it leads to reduction of the accuracy. To enhance the accuracy of iris segmentation, therefore, this study was carried-out using Integro-differential Operator approach in the segmentation process with the aim of locating the iris region of eye image, by employing one centre of the iris and pupil. This approach is found more effective in emphasizing the accuracy of iris segmentation. The evaluation was carried-out at the end of the study using CASIA-IrisV3-Intervals Database. The results of the experimental evaluation showed that the accuracy of the iris recognition increased, and the speed was acceptable.