J4 ›› 2010, Vol. 48 ›› Issue (05): 793-798.

• 数学 • 上一篇    下一篇

基于ROI归一化的ICA/PCA虹膜识别方法

王俊勇, 张长海, 刘元宁, 朱晓冬, 何飞   

  1. 吉林大学 计算机科学与技术学院, 长春 130012
  • 收稿日期:2009-09-02 出版日期:2010-09-26 发布日期:2010-09-21
  • 通讯作者: 刘元宁 E-mail:liuyn@jlu.edu.cn

ICA/PCA Iris Recognition Method Based on ROI Normalization

WANG Junyong, ZHANG Changhai, LIU Yuanning, ZHU Xiaodong, HE Fei   

  1. College of Computer Science and Technology, Jilin University, Changchun 130012, China
  • Received:2009-09-02 Online:2010-09-26 Published:2010-09-21
  • Contact: LIU Yuanning E-mail:liuyn@jlu.edu.cn

摘要:

针对虹膜识别中使用传统归一化方法时, 无法突出主要纹理信息, 并且由于提取数据量大导致特征提取阶段计算复杂的缺陷, 提出一种基于感兴趣区域(ROI)的虹膜归一化方法, 先利用主成分分析(PCA)方法提取主元, 实现进一步的降维和去噪, 再使用独立分量分析(ICA)进行训练形成ICA/PCA虹膜特征提取算法, 最后使用余弦距分类器对待测样本进行分类. 实验结果表明, 该方法识别率为98.11%, 识别时间小于70 ms.

关键词: 模式识别; 虹膜识别; 感兴趣区域

Abstract:

In view of the shortcomings of redundant data leading to computational complexity of feature extraction after traditional normalization in iris recognition and weakening of main texture information, we introduced the ROIbased iris normalization means and used PCA to extract principal component to reduce the dimension and remove noise further, then trained feature vectors using ICA to make ICA/PCA iris feature extraction algorithm; finally used cosine distance classifier to identify testing samples. Experimental recognition rate was reached up to 98.11%, and recognition time was less than 70 ms.

Key words: pattern recognition; iris recognition; region of interest(ROI)

中图分类号: 

  • TP18