基于手背静脉虹膜和指纹融合身份识别算法  

Personal Identity Recognition Algorithm Based on Fusion of Hand Vein,Iris and Fingerprint

作　　者：李秀艳[1] 刘铁根[1] 邓仕超[1] 

机构地区：[1]天津大学精密仪器与光电子工程学院光电信息技术科学教育部重点实验室,天津300072

出　　处：《光电工程》2010年第8期104-110,共7页Opto-Electronic Engineering

基　　金：国家重点基础研究发展计划(2010CB327802);国家自然科学基金(60627002;30770597);天津市应用基础研究计划(06YFJZJC00400);教育部博士点新教师基金(200800561020);教育部博士点基金(20090032110051);天津大学青年教师培养基金(TJU-YFF-08B47)资助项目

摘　　要：针对单模态生物特征识别的局限性,提出融合手背静脉、虹膜和指纹三种生物特征实现身份识别。首先分别对手背静脉图像、虹膜图像和指纹图像进行独立的图像预处理、特征提取和特征匹配,输出各自的匹配分数。分析匹配分数归一化对识别性能的影响,采用Tanh归一化方法对三种生物特征的匹配分数进行归一化处理,最后利用加权求和法则实现匹配分数的融合,利用最小距离分类器实现身份识别。实验结果表明,融合识别算法的等错率为0.009%,当错误接受率接近0时,对应的错误拒绝率仅为0.2%。Because of the limitation of single biometric recognition,a new multimodal biometric system based on hand vein,iris and fingerprint was proposed.Firstly,the hand vein image,iris image and fingerprint image were separately sent to image preprocessing module,feature extraction module and feature matching module,respectively.And the respective matching scores were obtained.The effects of score normalization on recognition performance were analyzed.Tanh normalization method was employed to perform the three scores normalization.Finally,the weighted sum principle was used to fulfill the scores fusion.Minimum distance classifier was adopted to personal identity decision.The experiments results show that Equal Error Rate（EER） of proposed recognition algorithm is 0.009%.When the False Acceptance Rate（FAR） is close to 0,the corresponding False Rejection Rate（FRR） at the same threshold is 0.2%.

关 键 词：生物特征识别 手背静脉 虹膜 指纹 匹配分数归一化 融合 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]