手指静脉特征的图表达与识别方法
Representation and Recognition Method of Finger-Vein Features Based on Graph
DOI: 10.12677/jisp.2025.142013, PDF,   
作者: 温梦娜, 叶子云, 赵子豪, 石滨萌：深圳职业技术大学粤港澳大湾区人工智能应用技术研究院，广东 深圳
关键词: 生物特征识别；手指静脉识别；图；图卷积神经网络；Biometric Recognition； Finger-Vein Recognition； Graph； Graph Convolutional Neural Network
摘要: 本文提出了一种手指静脉特征图表达与识别方法。首先，构建轻量型卷积神经网络用于提取手指静脉特征。然后，根据一定的生成规则将手指静脉特征转化为图网络结构，实现手指静脉特征的图表达。最后，构建图卷积神经网络用于手指静脉特征图数据的分类识别。实验结果表明，该方法的识别准确率能够达到92.35%，说明我们提出的方法能够完成手指静脉特征的有效识别。
Abstract: This paper proposes a finger-vein features representation and recognition method based on graph. First, a lightweight CNN model is constructed to extract finger-vein features. Then, feature maps output from CNN are transformed into graph network complying with generation rule. Finally, a graph convolutional neural network is constructed for classification of graph which is from finger-vein features. The experimental results show that the recognition accuracy of this method can reach 92.35%, indicating that the proposed method can effectively recognize finger-vein features.
文章引用：温梦娜, 叶子云, 赵子豪, 石滨萌. 手指静脉特征的图表达与识别方法[J]. 图像与信号处理, 2025, 14(2): 132-138. https://doi.org/10.12677/jisp.2025.142013

参考文献

[1] 张大鹏. 先进生物特征识别技术的研究与发展[J]. 机器人产业, 2020(6): 57-61.
[2] 牛妞, 王洁, 程君霞, 程瑛璠, 等. 指静脉识别技术的应用前景研究[J]. 电脑知识与技术, 2021, 17(12): 190-191.
[3] 秦华锋. 手指静脉识别技术研究[D]: [硕士学位论文]. 重庆: 重庆理工大学, 2009.
[4] Syazana-Itqan, K., Syafeeza, A.R., Saad, N.M., Hamid, N.A. and Bin Mohd Saad, W.H. (2016) A Review of Finger-Vein Biometrics Identification Approaches. Indian Journal of Science and Technology, 9, 1-8. [Google Scholar] [CrossRef] 
[5] 杨如民, 许琳英, 余成波. 基于Hessian矩阵和Gabor滤波的手指静脉特征提取[J]. 四川兵工学报, 2019, 40(3): 103-107.
[6] 刘海英. 基于二值局部特征的手指静脉识别方法研究[D]: [博士学位论文]. 济南: 山东大学, 2019.
[7] Dev, R. and Khanam, R. (2017) Review on Finger Vein Feature Extraction Methods. 2017 International Conference on Computing, Communication and Automation (ICCCA), Greater Noida, 5-6 May 2017, 1209-1213. [Google Scholar] [CrossRef] 
[8] Qin, H. and El-Yacoubi, M.A. (2017) Deep Representation-Based Feature Extraction and Recovering for Finger-Vein Verification. IEEE Transactions on Information Forensics and Security, 12, 1816-1829. [Google Scholar] [CrossRef] 
[9] Sarala, R., Yoghalakshmi, E. and Ishwarya, V. (2019) Finger Vein Biometric Based Secure Access Control in Smart Home Automation. International Journal of Engineering and Advanced Technology, 8, 851-855. [Google Scholar] [CrossRef] 
[10] 仲贞. 手指特征粒的鲁棒性内涵表达方法研究[D]: [硕士学位论文]. 天津: 中国民航大学, 2016.
[11] Yang, L., Yang, G., Yin, Y. and Zhou, L. (2014) A Survey of Finger Vein Recognition. In: Sun, Z., Shan, S., Sang, H., Zhou, J., Wang, Y. and Yuan, W., Eds., Biometric Recognition, Springer, 234-243. [Google Scholar] [CrossRef] 
[12] Das, R., Piciucco, E., Maiorana, E. and Campisi, P. (2019) Convolutional Neural Network for Finger-Vein-Based Biometric Identification. IEEE Transactions on Information Forensics and Security, 14, 360-373. [Google Scholar] [CrossRef] 
[13] Tang, S., Zhou, S., Kang, W., Wu, Q. and Deng, F. (2019) Finger Vein Verification Using a Siamese CNN. IET Biometrics, 8, 306-315. [Google Scholar] [CrossRef] 
[14] Levie, R., Monti, F., Bresson, X. and Bronstein, M.M. (2018) CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filters. arXiv: 1705.07664.
[15] 叶子云, 杨金锋. 一种基于加权图模型的手指静脉识别方法[J]. 山东大学学报(工学版), 2018, 48(3): 103-109.