Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (7): 165-167.DOI: 10.3778/j.issn.1002-8331.2010.07.050

• 图形、图像、模式识别 • Previous Articles     Next Articles

Rapid algorithm of iris localization

DU De-sheng1,GAO Xue-lian1,ZHANG Ge-sen2   

  1. 1.College of Automation,Harbin University of Science and Technology,Harbin 150080,China
    2.College of Information and Telecommunication Engineering,Harbin Engineering University,Harbin 150001,China
  • Received:2008-09-17 Revised:2008-12-04 Online:2010-03-01 Published:2010-03-01
  • Contact: DU De-sheng

一种快速虹膜定位方法

杜德生1,高雪莲1,张格森2   

  1. 1.哈尔滨理工大学 自动化学院,哈尔滨 150080
    2.哈尔滨工程大学 信息与通信工程学院,哈尔滨 150001
  • 通讯作者: 杜德生

Abstract: Iris localization is a very important part of iris recognition.Initial located point in pupil is gotten by average gray method.A novel pupil localization algorithm is proposed based on the edge detection template and C-means dynamic clustering algorithm is brought up to improve precision in localization.What is more,on the base of rude localization of outer boundary,accurate localization method of outer boundary is improved.Not only the time cost in the iris localization is sharply shortened but also the precision is improved by the algorithm combining rude localization with accurate localization.Many experiments indicate that the algorithm is easy,reliable,high-precision and encouraging performance are ensured.

Key words: iris localization, iris recognition, edge detection, clustering analysis

摘要: 虹膜定位是虹膜识别中非常重要的一个环节。首先利用灰度平均值法找到瞳孔内初始定位点,并提出一种通过边缘检测模板的新瞳孔定位方法,同时引入C-均值动态聚类分析法提高定位精度。然后在外边界粗定位的基础上,改进了虹膜外边界的精确定位方法,采用此种粗定位与精定位相结合的方法极大缩短了虹膜定位的时间,提高了定位的准确性。大量实验表明,该虹膜定位方法简单可靠,精确度高,取得了非常好的定位效果。

关键词: 虹膜定位, 虹膜识别, 边缘检测, 聚类分析

CLC Number: