计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (23): 201-202.DOI: 10.3778/j.issn.1002-8331.2008.23.060

• 图形、图像、模式识别 • 上一篇    下一篇

一种新的基于完整相位分析的虹膜分类算法

岳学东1,刘 洋2,3   

  1. 1.郑州大学 物理工程学院,郑州 450052
    2.中国科学院 西安光学精密机械研究所,西安 710119
    3.中国科学院 研究生院 北京 100039
  • 收稿日期:2007-10-18 修回日期:2008-01-16 出版日期:2008-08-11 发布日期:2008-08-11
  • 通讯作者: 岳学东

Novel iris classification algorithm based on complete phase analysis

YUE Xue-dong1,LIU Yang2,3   

  1. 1.College of Physical Science and Technology,Zhengzhou University,Zhengzhou 450052,China
    2.Xi’an Institute of Optics and Precision Mechanics,Chinese Academy of Sciences,Xi’an 710119,China
    3.Graduate School of the Chinese Academy of Sciences,Beijing 100039,China
  • Received:2007-10-18 Revised:2008-01-16 Online:2008-08-11 Published:2008-08-11
  • Contact: YUE Xue-dong

摘要: 将预处理后的虹膜图像分成64幅子块,并分别进行特征提取,然后按顺序提取每幅子图像完整的相位信息,建立相位特征向量,最后通过对特征向量进行内积运算获得虹膜样本之间的归一化分类距离。实验结果表明,该算法思路简洁,识别效果好,为虹膜分类研究提供了一种新的参考途径。

关键词: 特征提取, 相位相关, 虹膜识别, 分类距离

Abstract: The preprocessed iris image is divided into 64 sub-blocks,and the iris features are extracted respectively.The complete phase information of the features is extracted to establish the feature vector of iris,and then the normalized classification distance of iris samples is obtained by plot operation.The experiment shows that the idea of the algorithm is concise and reasonable,and its recognition effect is better.What’s more,it also offers a new way for iris classification research.

Key words: feature extraction, phase correlation, iris recognition, classification distance