Iris Segmentation from Video

Iris pattern is the most reliable biometric in terms of recognition and identification performance. Nowadays iris recognition base on video is growing rapidly. In order to obtain a robust identification system, it requires a fast and accurate iris segmentation method to improve the recognition rate. In this paper we perform four optimizations to automates our previous segmentation method and reduce the computing time to localize pupil and limbus boundary using a Circular Hough Transform. The pixel intensities where analyzed a histogram to detect and eliminate the sclera, eyelid and strong reflection region. In addition we analyze and implement a bank of Gabor filter to remove the eyelashes in order to obtain a fast iris region from video and free of noise.