Automated Iris Segmentation and Robust Features Extraction Based on Parallel SURF Feature Model

Iris Recognition stands out as one of the most accurate biometric methods in use today. However, the iris segmentation and recognition algorithms are currently implemented on general purpose sequential processing systems, such as generic central processing units (CPUs). In this paper, we have proposed a new method for automatic IRIS segmentation in order to humans identification applications using the graphics processing unit (GPU). The parallel Hough transform has been used to detect the border between iris and pupil. The coordinate and radius of pupil has been used to detect the border between iris and sclera. Moreover, after omitting eyelashes based on the proposed algorithm, a degree two parabolic crossing from eyelid points is used to define eyelid edges. Finally, the GPU based parallel SURF features extracting algorithm is used to extract robust features of iris area. The propose method has been evaluated on CASIA iris dataset and the results show more than 97% True Detection Rate.