Iris Image Segmentation Based on K-means Cluster

摘要：

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-Mcans 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.

关键词： Iris segmentation K-Means clustering Boundayr detection

作者: Liu Jin Fu Xiao Wang Haopeng

作者单位: Department of Fundamental Courses Air Force,Aviation University Changchun, China Department of Fundamental Courses Air Force Aviation University Changchun, China Elementary Flight Training Base Air Force Aviation University Changchun,China

会议类型: 国际会议

会议名称: 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems(2010 IEEE 智能计算与智能系统国际会议 ICIS 2010)

会议地点: 厦门

会议语种:英文

页码: 194-198

在线出版日期: 2010-10-29（万方平台首次上网日期，不代表论文的发表时间）