基于相对距离和角度的手指静脉识别方法  

Finger vein recognition method based relative distance and angle

作　　者：王科俊[1] 刘靖宇[1] 

机构地区：[1]哈尔滨工程大学自动化学院,黑龙江哈尔滨150001

出　　处：《华中科技大学学报（自然科学版）》2011年第5期96-99,共4页Journal of Huazhong University of Science and Technology(Natural Science Edition)

基　　金：国家自然科学基金资助项目(60975022);国家高技术研究发展计划资助项目(2008AA01Z148);黑龙江省杰出青年基金资助项目(JC200703);黑龙江省优秀学科带头人基金资助项目(2007REXXG009)

摘　　要：根据以静脉图像拓扑结构的本质特性,提出了一种新的手指静脉识别方法.首先对细修复后的手指静脉提取交叉点;然后计算这些交叉点之间的相对距离和交叉点连线产生的夹角;最后将这2种特征融合,进行手指静脉识别.该方法结合静脉自身特征,充分利用了拓扑结构的本质属性,无须定位,一定程度上克服了图像平移、旋转对识别结果的影响.实验结果表明:该方法能够快速准确地进行身份识别,具有实际应用价值.According to the essential characters of the image topology, a finger vein recognition meth- od was proposed. The intersectant points from the repaired and thinned finger vein image were extracted. Then the relative distance between the intersection point and the angle produced by the intersection point connections were calculated. Finallythese two features were combined for finger vein recognition. This method combined with the self characteristics of finger vein which make full use of the essential attribute of the topology without location can effectively overcome the influence on the recognition results caused by image translation and rotation. The experimental results show that the identification fast and accurately can be achieved through the proposed method which has great practical value and prospect.

关 键 词：手指静脉识别 拓扑结构 特征融合 相对距离 角度 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]