2025年 05期

摘要(Abstract)：

针对注册图像与测试图像的面积差异引起的跨面积识别问题，提出一种基于候选匹配区域定位的跨面积手指静脉识别方法。按步长切割每幅注册图像，得到多个与小面积测试图像面积相同的图像块，对小面积测试图像使用注册图像块稀疏表示，将系数不为0的图像块作为测试图像的候选匹配区域；分别使用手指静脉灰度图像和静脉主干分别定位上述候选匹配区域，并融合2个候选匹配区域集合；提取测试图像与候选匹配区域的局部二值模式特征，基于汉明距离将测试图像与一幅图像多个候选区域的局部二值模式特征进行一对多匹配，进而基于计算得到的多个汉明距离的最小值识别测试图像。在2个公开手指静脉数据库实验验证所提方法的识别性能。结果表明：所提方法在香港理工大学手指静脉数据库、山东大学手指静脉数据库的识别率分别为94.34%和81.45%,优于现有的4种手指静脉识别方法，验证了该方法在跨面积手指静脉识别中的有效性。

关键词(KeyWords)：手指静脉识别;跨面积识别;候选匹配区域定位;稀疏表示;静脉主干

基金项目(Foundation):国家自然科学基金项目(62076151);; 山东省高等学校青创团队计划项目(2022KJ205)

作者(Author): 施秀峰,迟云浩,杨璐

DOI:10.13349/j.cnki.jdxbn.20250716.001

参考文献(References)：

[1] LI S Y,ZHANG B,FEI L K,et al.Joint discriminative feature learning for multimodal finger recognition[J].Pattern Recognition,2021,111:107704.

[2] QIN H F,HU R S,El-YACOUBI M A.Local attention transformer-based full-view finger-vein identification[J].IEEE Transactions on Circuits and Systems for Video Technology,2022,33:2767.

[3] KIRCHGASSER S,KAUBA C,LAI Y L,et al.Finger vein template protection based on alignment-robust feature description and index-of-maximum hashing[J].IEEE Transactions on Biometrics,Behavior,and Identity Science,2020,2(4):337.

[4] WU J D,YE S H.Driver identification using finger-vein patterns with radon transform and neural network[J].Expert Systems with Application,2009,36(3):5793.

[5] HUANG J D,LUO W J,YANG W L,et al.FVT:finger vein transformer for authentication[J].IEEE Transactions on Instrumentation and Measurement,2022,71:5011813.

[6] ZHAO P Y,CHEN Z Q,XUE J H,et al.Single-sample finger vein recognition via competitive and progressive sparse representation[J].IEEE Transactions on Biometrics,Behavior,and Identity Science,2022,5(2):209.

[7] 李菲，李小霞，周颖玥，等.基于改进HOG特征和稀疏表示的手指静脉识别[J].传感器与微系统，2018,37(11):38.

[8] 王艳芳，陈磊，黄经纬.基于非局部稀疏去噪与LBP算法的指静脉识别[J].自动化应用，2020(10):21.

[9] ZHOU L Z,YANG L,FU D Q,et al.Encoding coefficient similarity-based multifeature sparse representation for finger vein recognition[J].IET Biometrics,2023,2023:9253739.

[10] LEI L,XI F,CHEN S Y,et al.A sparse representation denoising algorithm for finger-vein image based on dictionary learning[J].Multimedia Tools and Applications,2021,80:15135.

[11] MIURA N,NAGASAKA A,MIYAKAFUMI T.Feature extraction of finger vein patterns based on repeated line tracking and its application to personal identification[J].Machine Vision and Applications,2004,15:194.

[12] MIURA N,NAGASAKA A,MIYAKAFUMI T.Extraction of finger-vein patterns using maximum curvature points in image profiles[J].IEICE Transcations on Information and Systems,2007,90(8):1185.

[13] YANG J F,SHI Y H,JIA G M.Finger-vein image matching based on adaptive curve transformation[J].Pattern Recognition,2017,66:34.

[14] KUMAR A,ZHOU Y B.Human identification using finger images[J].IEEE Transactions on Image Processing,2012,21(4):2228.

[15] LIU F,YANG G P,YIN Y L,et al.Singular value decomposition based minutiae matching method for finger vein recognition[J].Neurocomputing,2014,145:75.

[16] MATSYDA Y,MIURA N,NAGASAKA A,et al.Finger-vein authentication based on deformation-tolerant feature-point matching[J].Machine Vision and Applications,2016,27:237.

[17] MENG X J,ZHENG J W,XI X M,et al.Finger vein recognition based on zone-based minutia matching[J].Neurocomputing,2021,423:110.

[18] KANG W X,LU Y T,LI D J,et al.From noise to feature:exploiting intensity distribution as a novel soft biometric trait for finger vein recognition[J].IEEE Transactions on Information Forensics and Security,2019,14(4):858.

[19] LU Y,XIE S J,YOON S,et al.Finger vein identification using polydirectional local line binary pattern[C]//2013 International Conference on ICT Convergence (ICTC),October 14-16,2013,Jeju,Republic Korea.New York:IEEE,2013:61.

[20] LU Y,YOON S,XIE S J,et al.Finger vein recognition using generalized local line binary pattern[J].KSII Transactions on Internet & Information Systems,2014,8(5):1766.

[21] KAPOOR K,RANI S,KUMAR M,et al.Hybrid local phase quantization and grey wolf optimization based SVM for finger vein recognition[J].Multimedia Tools and Applications,2021,80(10):15233.

[22] ZHANG Z X,WANG M W.A simple and efficient method for finger vein recognition[J].Sensors,2022,22(6):2234.

[23] YANG W L,LUO W,KANG W X,et al.FVRAS-Net:an embedded finger-vein recognition and antispoofing system using a unified CNN[J].IEEE Transactions on Instrumentation and Measurement,2020,69(11):8690.

[24] CHANG R C H,WANG C Y,LI Y H,et al.Design of low-complexity convolutional neural network accelerator for finger vein identification system[J].Sensors,2023,23(4):2184.

[25] WANG Y,SHI D K,ZHOU W B.Convolutional neural network approach based on multimodal biometric system with fusion of face and finger vein features[J].Sensors,2022,22(16):6039.

[26] 汪凯旋，陈光化，褚洪佳.基于改进的ResNet手指静脉识别[J].激光与光电子学进展，2021,58(20):100.

[27] SHAHEED K,MAO A H,QURESHI I,et al.DS-CNN:a pre-trained Xception model based on depth-wise separable convol-utional neural network for finger vein recognition[J].Expert Systems with Applications,2022,191:116288.

[28] YIN Y L,LIU L L,SUN X W.SDUMLA-HMT:a multimodal biometric database[M]//SUN Z N,LAI J H,CHEN X L,et al.Biometric Recognition(CCBR 2011):Lecture Notes in Computer Science,Vol 7098.Berlin,Heidelberg:Springer,2011:260.

[29] SHAZEEDA S,ROSDI B A.Nearest centroid neighbor based sparse representation classification for finger vein recognition[J].IEEE Access,2019,7:5874.

[30] SHAZEEDA S,ROSDI B A.Finger vein recognition using mutual sparse representation classification[J].IET Biometrics,2019,8(1):49.

[31] SHI X F,YANG L,GUO J,et al.Cross-area finger vein recognition via hierarchical sparse representation[M]//LIU Q S,WANG H Z,MA Z Y,et al.Pattern Recognition and Computer Vision(PRCV 2023):Lecture Notes in Computer Science,Vol 14429.Singapore:Springer,2023:86.