基于Haar小波的虹膜特征提取算法  

Iris Feature Extraction Based on Haar Wavelet

作　　者：孙冬[1] 周俊[2] 魏勇[1] 

机构地区：[1]河南机电高等专科学校,新乡453000 [2]后勤工程学院,重庆401331

出　　处：《科学技术与工程》2014年第1期81-85,共5页Science Technology and Engineering

基　　金：河南省高等学校青年骨干教师计划项目(教高[2011]873号)资助;重庆市博士后科研项目(XM2012049)特别资助

摘　　要：虹膜特征提取算法的优劣决定了虹膜识别系统的性能,经典小波变换算法在特征提取上存在不足,提出一种利用二维Haar小波提取虹膜特征的算法。算法在虹膜预处理的基础上,利用2D Haar小波对虹膜特征提取区域分解,对第三层小波分解高频系数编码生成375bits虹膜编码,利用相似度作为特征匹配关系。在中国科学院虹膜数据库[CASIA(1.0)]上的实验结果表明,算法在认证模式(Verification)与识别模式(Identification)下,性能均优于Boles的算法和Wildes的算法,仅次于Daugman的算法;但本算法虹膜码长度仅为Daugman的1/5,更节省储存空间,正确识别率为99.16%,等错率达到0.54%。The performance of iris recognition system is determined largely by the iris feature extraction algorithm. To improve the accuracy of iris recognition system, an efficient algorithm is proposed for iris feature extraction based on 2D Haar wavelet. Firstly, the iris image is decomposed by the 2D Haar wavelet three times, and then a 375-bit iris code is obtained by quantizing all the high-frequency coefficients at third lever. Finally similarity degree function is used as matching scheme. Experimental results on CASIA iris database show that algorithm has attractive performances than algorithm from Boles and Wildes, only inferior to Daugman＇s algorithm, but the length of our iris code is only one-fifth comparing with Daugman,s. The proposed algorithm has the encouraging correct recognition rate （CRR） which is 99.16%, accompan- ying with very low equal error rate （EER） 0.54%.

关 键 词：虹膜特征提取Haar小波 小波分解 细节系数调制 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]