Fast Iris Localization Based on Improved Hough Transform

Iris is a new biometric emerging in recent years. Iris identification is gradually applied to a number of important areas because of its simplicity, fast identification and low error recognition rate. Typically, an iris recognition system includes four parts: iris localization, feature extraction, coding and recognition. Among it, iris localization is a critical step. In the paper, a fast iris localization algorithm based on improved Hough transform was proposed. First, the algorithm builds gray histogram of iris image to analyze the gray threshold of the iris boundary. Then takes the pupil image binarization, using corrosion and expansion or region growing to remove noise. As a result, it obtains the radius of the inner edge. Then, we conduct iris location based on Hough transform according to the geometrical feature and gray feature of the human eye image. By narrowing searching scope, localization speed and iris localization accuracy are improved. Besides, it has better robustness for real-time system. Experimental results show that the proposed method is effective and encouraging.