吉林大学学报(信息科学版) ›› 2016, Vol. 34 ›› Issue (1): 73-78.

• 论文 • 上一篇    下一篇

基于特征点距离的手背静脉特征融合方法

任桐慧1a, 刘摇富1a, 姜守坤1a, 王摇贺1a, 杨摇悦1b,2   

  1. 1. 吉林大学a. 通信工程学院; b. 交通学院, 长春130022; 2. 长春光华学院电气信息学院, 长春130031
  • 收稿日期:2015-09-14 出版日期:2016-01-25 发布日期:2016-05-10
  • 作者简介:任桐慧(1990—), 女, 长春人, 吉林大学硕士研究生, 主要从事模式识别与智能系统研究, (Tel)86-18604403635 (E-mail)1160068448@ qq.com;刘富(1968—), 男, 长春人, 吉林大学教授, 博士生导师, 主要从事模式识别与智能系 统研究,(Tel)86-13610708679(E-mail)liufu@ jlu. edu. cn。
  • 基金资助:

    吉林省科技厅基金资助项目(201402040467)

Fusion Method Based on Feature Point Distance of Hand Vein

REN Tonghui1a, LIU Fu1a, JIANG Shoukun1a, WANG He1a, YANG Yue1b,2   

  1. 1a. College of Communication Engineering; 1b. College of Transportation Engineering, Jilin University, Changchun 130022, China;2. College of Electrical Information, Changchun Guanghua University, Changchun 130031, China
  • Received:2015-09-14 Online:2016-01-25 Published:2016-05-10

摘要:

针对现有手背静脉识别利用手背静脉特征较少, 识别率较低的问题, 提出了一种基于特征点距离的手背静脉特征融合方法。该方法首先对手背静脉进行细化, 对不变矩特征的量化值求和再进行匹配; 然后提取手背静脉的端点及交叉点, 利用改进的Hausdorff 距离进行匹配, 从而去除零距离点的影响, 提高两幅图之间的非相似性; 最后将这两种匹配方法进行加权融合。实验证明, 该融合算法识别率可达96. 75%, 且运行时间仅为0. 97 s。

关键词: 生物识别, 手背静脉, 特征点, 不变距, Hausdorff 距离, 加权融合

Abstract:

In order to solve the shortcoming of fewer hand vein characteristics and lower recognition rates of hand vein recognition, we proposed a fusion method based on feature point distance of hand vein. Firstly, the hand vein is refined and matched the sum of quantized values of moment invariants feature; then the endpoints and the intersections of hand vein is extracted, and the improved Hausdorff distance is used to match, so the effects of zero point was removed, the degree of dissimilarity between two images was increased; finally, the two methods are weighted and fused. The experimental results show that fusion algorithm recognition rate can reach 96. 75%, and the running time is 0. 97 s.

Key words: biometrics, hand vein, feature points, moment invariants, Hausdorff distance, weighted fusion

中图分类号: 

  • TP391. 4