东北大学学报（自然科学版）

东北大学学报(自然科学版) ›› 2010, Vol. 31 ›› Issue (7): 938-941.DOI: -

• 论著 • 上一篇    下一篇

基于椭圆拟合的晃动虹膜图像的检测算法

王琪;张祥德;印雨;张铁;   

  1. 东北大学理学院;
  • 收稿日期:2013-06-20 修回日期:2013-06-20 出版日期:2010-07-15 发布日期:2013-06-20
  • 通讯作者: -
  • 作者简介:-
  • 基金资助:
    国家自然科学基金资助项目(50704012)

A detection method for motion-blurred iris image based on ellipse fitting

Wang, Qi (1); Zhang, Xiang-De (1); Yin, Yu (1); Zhang, Tie (1)   

  1. (1) School of Sciences, Northeastern University, Shenyang 110004, China
  • Received:2013-06-20 Revised:2013-06-20 Online:2010-07-15 Published:2013-06-20
  • Contact: Zhang, X.-D.
  • About author:-
  • Supported by:
    -

RichHTML

0

PDF (PC)

779

摘要： 针对虹膜识别系统中晃动影响识别准确率的问题,提出了一种基于椭圆拟合的晃动虹膜图像的检测算法.首先对虹膜区域利用Gabor滤波器卷积初步估计光斑的位置;然后在放大5倍的截取虹膜图像上定位有效光斑;最后,对每个光斑的边界进行椭圆拟合,并计算长短轴比例和拟合误差,误差较小且长短轴比例大于1.55的图像判定为晃动图像.在CASIA-IrisV3-Lamp数据库上的实验表明,该方法检测晃动虹膜图像的准确率达到100%,提高了虹膜识别系统的准确率.

关键词: 虹膜识别, 晃动虹膜图像, Gabor滤波器, 光斑检测, 椭圆拟合

Abstract: A detection method for motion-blurred iris images was developed based on ellipse fitting to make the iris recognition system more accurate. The positions of luminous spots were estimated preliminarily in iris image by Gabor filter, then the actual luminous spot was detected in iris image which has been magnified to 5 times. With the ellipse fitting done to the boundary of every luminous spots, the fitting error and the ratio of major axis to minor axis are both calculated. An image could be judged as a motion-blurred one if the ratio is greater than 1.55 with relatively small fitting error. Results of the experiments carried out on CASIA-IrisV3-Lamp database indicated that the accuracy of detection of motion-blurred images is up to 100%, thus improving the accuracy of the whole iris recognition system.

中图分类号: