基于局部宏观结构和微观特征融合的手指静脉识别算法  

Finger Vein Recognition Algorithm based on Local Macrostructure and Micro-feature Fusion

作　　者：程申前 游林[1] CHENG Shen-qian;YOU Lin(College of Communication Engineering,Hangzhou Dianzi University,Hangzhou Zhejiang 310018,China)

机构地区：[1]杭州电子科技大学通信工程学院,浙江杭州310018

出　　处：《通信技术》2018年第7期1585-1593,共9页Communications Technology

基　　金：国家自然科学基金项目(No.61772166);国家自然科学基金项目(No.61272045);浙江省自然科学基金重点项目(No.LZ17F020002)~~

摘　　要：针对局部二元模式及其改进模式在静脉特征提取时无法兼顾局部宏观结构和微观特征的问题,提出了一种新的基于局部宏观结构和微观特征融合的局部二元模式(LMMF-LBP),以更准确地表征静脉特征信息,并利用图像分块和加权模板设计了基于LMMF-LBP算子的手指静脉识别算法。研究结果表明:基于LMMF-WPLBP的静脉识别算法不仅能够提高识别性能,而且具有更好的鲁棒性。In finger vein feature extraction,the local binary model and its improved model cannot simultaneously represent the local macrostructure and microscopic feature information.To solve this problem,a novel local binary model local binary pattern based on local macrostructure and microfeature fusion(LMMF-LBP)is proposed,so as to characterize vein features more accurately.Then,Finger vein recognition algorithm based on LMMF-LBP is designed by using partition and weighted template.The experiment results indicate that the finger vein recognition algorithm based on LMMF-WPLBP could improve the recognition performance while being of fairly strong robustness.

关 键 词：手指静脉识别 特征提取 局部二元模式 LMMF-LBP 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]