基于特征融合的手背静脉识别  

Hand Vein Recognition Based on Feature Fusion

作　　者：胡云朋[1,2] 王志勇 李飞 杨晓苹 薛玉明 

机构地区：[1]天津理工大学电子信息工程学院 [2]天津市薄膜电子与通信器件重点实验室,天津300384

出　　处：《光子学报》2014年第1期151-155,共5页Acta Photonica Sinica

基　　金：天津市科技支撑重点项目(No.12ZCZDGX02700)资助

摘　　要：图像平移和旋转会降低手背静脉识别的准确性,针对该问题,本文提出了一种特征融合的手背静脉识别法.该方法充分考虑图像的细节特征和全局特征,首先选取图像中的交叉点和端点作为特征点,再从特征点中提取出图像匹配的基准点,计算基准点至特征点间的相对距离及基准点与特征点连线间相邻连线产生的夹角作为细节特征;然后利用不变矩方法提取图像特征作为全局特征;最后将两种图像特征融合,进行手背静脉识别.实验模拟结果表明,该方法可快速有效地实现手背静脉识别.Image translation and rotation reduces the accuracy of hand vein recognition. Aiming at this problem, a new hand vein recognition algorithm was proposed based on multi-feature fusion. The characteristic of the approach was to combine local and global features for hand vein recognition. Firstly, intersection points and endpoints were selected as feature points. The reference point for image matching was extracted from feature points. The relative distances between the reference points to feature points were computed. The angles between the adjacent connections were calculated and used as local features. Then the moment invariants were calculated as global features. Finally these features were combined for hand vein recognition. Experimental results show that the proposed algorithm is able to achieve hand vein recognition reliably and quickly.

关 键 词：生物光学 静脉识别 特征融合 生物测量学 特征提取 基准点 算法 目标识别 矩方法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]