基于小波变换和方向向量的虹膜特征提取方法  

Iris feature extraction algorithm based on wavelet transform and directional vector

作　　者：王凤随[1] 冯桂[1] 

机构地区：[1]华侨大学信息科学与工程学院,福建泉州362021

出　　处：《计算机工程与设计》2008年第14期3829-3830,F0003,共3页Computer Engineering and Design

基　　金：福建省自然科学基金项目(A0610022);国务院侨办科研基金项目(06QZR03)

摘　　要：虹膜纹理上的差异是不同虹膜相互区别的最主要原因和体现。因此,要想获得很高的虹膜识别率,就要有效地提取虹膜的纹理信息。基于二维小波变换和方向向量,提出一种新的虹膜特征提取方法。该方法的基本思想是考虑虹膜纹理的灰度变化,对于多层小波分解后的低频分量,分别求其在4个方向上的方向向量,最后形成虹膜码。测试结果表明,该方法能有效地提高虹膜的识别率,且算法简单、快速。Irises can be distinguished mainly due to textural difference among them. In order to acquire a high recognition rate, the textural information of iris images must be extracted effectively. A new iris feature extraction method is presented by taking advantages of 2-D wavelet transform. The basic principle of the method is as follows. In view of iris textural intensity variation, for the lowfrequency components of multi-resolution decomposition, directional vector along four directions is obtained, and iris code is formed in the end. According to test, the algorithm can enhance iris recognition rate. Furthermore, algorithm is simple and fast.

关 键 词：虹膜识别 特征提取 小波变换 方向向量 识别率 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]