正在加载图片...
工程科学学报,第37卷,第7期:965970,2015年7月 Chinese Journal of Engineering,Vol.37,No.7:965-970,July 2015 DOI:10.13374/j.issn2095-9389.2015.07.020:http://journals.ustb.edu.cn 基于局部宏观特征和微观特征结合的手背静脉身份 识别 王一丁”,于晓婕,李琛”,穆志纯》 1)北方工业大学信息工程学院,北京1000412)北京科技大学自动化学院,北京100083 ☒通信作者,E-mail:gengyuan927@163.com 摘要手背静脉身份识别由于其非接触和不易被污染等独特的优势,已成为各种新型生物特征识别手段中的研究和应用 热点.如何提取具有高鉴别性且鲁棒的手背静脉图像特征是本文的研究重点.本文简述了基于局部二值模式(local binary pattern,LBP)的特征提取方法及其改进方法的基本原理,讨论分析了其不足,并针对不足,提出了一种多尺度块中心对称局 部二值模式(nulti-scale block center-symmetric LBP,MB-CSLBP)算子.本文所提出的MB-CSLBP算子既考虑图像的局部宏观 特征,也兼顾图像的微观特征,获取了更加全面的图像信息.在自建的2040幅近红外手背静脉图像数据库中,用MB-CSLBP 方法获取图像特征并使用最近邻分类器进行识别.大量的对比实验结果表明,本文所提方法的识别率达到98.21%,优于原 始LBP及其改进算子,中心对称局部二值模式(center-symmetric LBP,CS-LBP)和多尺度块局部二值模式(multi-scale block LBP,MB-LBP)等. 关键词身份识别:手;静脉:特征提取:宏观特征:微观特征 分类号TP391.41 Hand-dorsa vein identification based on local macroscopic and microscopic characteristics WANG-ding”,YU Xiao-jie,I Chen”,MU Zhi--thun 1)School of Information Engineering,North China University of Technology,Beijing 100041,China 2)School of Automation and Electrical Engineering,University of Science and Technology Beijing,Beijing 100083,China Corresponding author,E-mail:gengyuan927@163.com ABSTRACT As hand-dorsa vein identification is non-contact,not easily polluted,and has other unique advantages,it becomes a new research and application hotspot of biometric identification methods.The focus of this paper is how to extract hand-dorsa vein image characteristics with high identification rate and robustness.This paper briefly describes the basic principle of local binary pattern (LBP)and improved LBP methods,and analyzes the disadvantages of these methods.A novel method called multi-scale block center- symmetric LBP(MB-CSLBP)is proposed.It includes not only the image's microstructures but also macrostructures,which can give more information of the image.This method is tested on a database of 2040 near-infrared hand-dorsa vein images using MB-CSLBP features and a nearest neighbor classifier.A large number of experimental results show that the proposed method offers a better recogni- tion result of 98.21%,outperforming the original LBP and improved LBP operators,such as CS-BP and MB-LBP. KEY WORDS identification:hands:veins;feature extraction:macroscopic characteristics;microscopic characteristics 利用手背静脉信息进行身份识别是近十几年发展起来的一种新的生物识别方法·可,手背静脉识别主 收稿日期:201403-30 基金项目:国家自然科学基金资助项目(61271368):北京市自然科学基金重点项目(KZ201410009013)工程科学学报,第 37 卷,第 7 期: 965--970,2015 年 7 月 Chinese Journal of Engineering,Vol. 37,No. 7: 965--970,July 2015 DOI: 10. 13374 /j. issn2095--9389. 2015. 07. 020; http: / /journals. ustb. edu. cn 基于局部宏观特征和微观特征结合的手背静脉身份 识别 王一丁1) ,于晓婕1) ,李 琛1) ,穆志纯2) 1) 北方工业大学信息工程学院,北京 100041 2) 北京科技大学自动化学院,北京 100083  通信作者,E-mail: gengyuan927@ 163. com 摘 要 手背静脉身份识别由于其非接触和不易被污染等独特的优势,已成为各种新型生物特征识别手段中的研究和应用 热点. 如何提取具有高鉴别性且鲁棒的手背静脉图像特征是本文的研究重点. 本文简述了基于局部二值模式( local binary pattern,LBP) 的特征提取方法及其改进方法的基本原理,讨论分析了其不足,并针对不足,提出了一种多尺度块中心对称局 部二值模式( multi-scale block center-symmetric LBP,MB-CSLBP) 算子. 本文所提出的 MB-CSLBP 算子既考虑图像的局部宏观 特征,也兼顾图像的微观特征,获取了更加全面的图像信息. 在自建的 2040 幅近红外手背静脉图像数据库中,用 MB-CSLBP 方法获取图像特征并使用最近邻分类器进行识别. 大量的对比实验结果表明,本文所提方法的识别率达到 98. 21% ,优于原 始 LBP 及其改进算子,中心对称局部二值模式( center-symmetric LBP,CS-LBP) 和多尺度块局部二值模式( multi-scale block LBP,MB-LBP) 等. 关键词 身份识别; 手; 静脉; 特征提取; 宏观特征; 微观特征 分类号 TP391. 41 Hand-dorsa vein identification based on local macroscopic and microscopic characteristics WANG Yi-ding1) ,YU Xiao-jie1)  ,LI Chen1) ,MU Zhi-chun2) 1) School of Information Engineering,North China University of Technology,Beijing 100041,China 2) School of Automation and Electrical Engineering,University of Science and Technology Beijing,Beijing 100083,China  Corresponding author,E-mail: gengyuan927@ 163. com ABSTRACT As hand-dorsa vein identification is non-contact,not easily polluted,and has other unique advantages,it becomes a new research and application hotspot of biometric identification methods. The focus of this paper is how to extract hand-dorsa vein image characteristics with high identification rate and robustness. This paper briefly describes the basic principle of local binary pattern ( LBP) and improved LBP methods,and analyzes the disadvantages of these methods. A novel method called multi-scale block center￾symmetric LBP ( MB-CSLBP) is proposed. It includes not only the image's microstructures but also macrostructures,which can give more information of the image. This method is tested on a database of 2040 near-infrared hand-dorsa vein images using MB-CSLBP features and a nearest neighbor classifier. A large number of experimental results show that the proposed method offers a better recogni￾tion result of 98. 21% ,outperforming the original LBP and improved LBP operators,such as CS-LBP and MB-LBP. KEY WORDS identification; hands; veins; feature extraction; macroscopic characteristics; microscopic characteristics 收稿日期: 2014--03--30 基金项目: 国家自然科学基金资助项目( 61271368) ; 北京市自然科学基金重点项目( KZ201410009013) 利用手背静脉信息进行身份识别是近十几年发展 起来的一种新的生物识别方法[1--5]. 手背静脉识别主
向下翻页>>
©2008-现在 cucdc.com 高等教育资讯网 版权所有