基于盒维的手掌静脉识别算法  

A Palm Vein Recognition Algorithm on Fractal Dimension

作　　者：郭秀梅[1] 王成义[1] GUO Xiu-mei;WANG Cheng-yi(College of Information Science and Engineering/Shandong Agricultural University,Tai’an 271018,China)

机构地区：[1]山东农业大学信息科学与工程学院,山东泰安271018

出　　处：《山东农业大学学报（自然科学版）》2018年第1期57-60,共4页Journal of Shandong Agricultural University：Natural Science Edition

基　　金：山东农业大学博士基金

摘　　要：静脉识别具有高度防伪、简易便用、高度准确等优点,成为近几年新兴的生物特征识别技术。鉴于静脉血管分布具有一定的自相似性,具有较好的分形特征,因此将分形维数应用于手掌静脉识别系统中,提出了基于盒维的静脉识别算法。该算法在Poly U波长为880 nm的近红外光掌纹数据库上进行了试验,实验结果表明,盒维可以很好的提取静脉特征,获得的识别率可达99.3%,识别速度小于70 ms,远远满足在线静脉识别系统。Palm vein recognition as a new biological recognition technology is widely studied in recent years.In view of the fractal dimension having relation to surface roughness,which the more complex image texture on the surface of the object,the greater the fractal dimension of this characteristic,this article applies fractal dimension to palm vein recognition system,and a palmvein recognition based on box dimension is proposed.The algorithm is tested on the near-infrared database of Hong Kong polytechnic university multispectral palmprint database.The experimental results show that the box dimension can extract palm vein feature effectively and efficiently with a high recognition rate 99.3%and less processing time 70 ms.

关 键 词：盒维 手掌静脉识别 算法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]