Iris image segmentation based on K-means cluster

Iris segmentation is an important step for automatic iris recognition. This paper presents a new iris segmentation method based on K-means clustering. we propose a limbic boundary localization algorithm based on K-Means clustering for pupil detection. We locates the centers of the pupil and the iris in the input image. Then two image strips containing the iris boundaries are extracted. The outer boundary of iris is localized based on shrunk image using Hough transform. The proposed method was evaluated in the UBIRIS.v2 testing database by the NICE.I organizing committee and results are well.