Feng-Zhao Lian, Jun-Duan Huang, Ji-Xin Liu, Guang Chen, Jun-Hong Zhao, Wen-Xiong Kang. FedFV: A Personalized Federated Learning Framework for Finger Vein Authentication. Machine Intelligence Research. https://doi.org/10.1007/s11633-022-1341-4
Citation: Feng-Zhao Lian, Jun-Duan Huang, Ji-Xin Liu, Guang Chen, Jun-Hong Zhao, Wen-Xiong Kang. FedFV: A Personalized Federated Learning Framework for Finger Vein Authentication. Machine Intelligence Research. https://doi.org/10.1007/s11633-022-1341-4

FedFV: A Personalized Federated Learning Framework for Finger Vein Authentication

doi: 10.1007/s11633-022-1341-4
More Information
  • Author Bio:

    Feng-Zhao Lian received the B. Sc. degree in automation from South China University of Technology, China in 2019. He is currently a master student at School of Automation Science and Engineering, South China University of Technology, China. His research interests include biometrics, federated learning, computer vision and deep learning. E-mail: lianfengzhaoscut@qq.com ORCID iD: 0000-0002-4219-067X

    Jun-Duan Huang received the B. Sc. degree in automation, and M. Sc. degree in agricultural electrification and automation, from South China Agriculture University, Guangzhou, China, in 2017 and 2020, respectively. He is currently a doctoral candidate in electronic and information at South China University of Technology, Guangzhou, China. His research interests include biometrics, computer vision, audio signal processing, deep learning and agricultural engineering. E-mail: runrunjun@163.com ORCID iD: 0000-0002-5510-7046

    Ji-Xin Liu received the M. Sc. degree in power electronics and power drives from Northeast Petroleum University, China in 2004, and the Ph. D. degree in information and communication engineering from Harbin Institute of Technology, China in 2010. He is currently an associate professor with School of Automation, Guangdong University of Petrochemical Technology, China. His research interests include biometric identification, privacy preserving machine learning, pattern recognition and fault diagnosis of petrochemical equipment. E-mail: ljxfrog@qq.com

    Guang Chen received the B. Sc. degree in mechatronics engineering from Xi′an University of Architecture and Technology, China in 2008. His research interests include biometric recognition, machine learning and federated learning. E-mail: cguang1@grgbanking.com

    Jun-Hong Zhao received the M. Sc. degree in pattern recognition and intelligent system from Chongqing University, China in 2003, and the Ph. D. degree in pattern recognition and intelligent system from South China University of Technology, China in 2011. She is currently a lecturer with School of Automation Science and Engineering, South China University of Technology, China. Her research interests include image processing, image forensics and biometrics identification. E-mail: jhzhao@scut.edu.cn (Corresponding author)

    Wen-Xiong Kang received the Ph. D. degree in systems engineering from South China University of Technology, China in 2009. He is currently a professor with School of Automation Science and Engineering, South China University of Technology, China.His research interests include biometrics identification, image processing, pattern recognition, and computer vision.E-mail: auwxkang@scut.edu.cn (Corresponding author) ORCID iD: 0000-0001-9023-7252

  • Received Date: 2022-04-17
  • Accepted Date: 2022-05-27
  • Publish Online: 2023-01-11
  • Most finger vein authentication systems suffer from the problem of small sample size. However, the data augmentation can alleviate this problem to a certain extent but did not fundamentally solve the problem of category diversity. So the researchers resort to pre-training or multi-source data joint training methods, but these methods will lead to the problem of user privacy leakage. In view of the above issues, this paper proposes a federated learning-based finger vein authentication framework (FedFV) to solve the problem of small sample size and category diversity while protecting user privacy. Through training under FedFV, each client can share the knowledge learned from its user′s finger vein data with the federated client without causing template leaks. In addition, we further propose an efficient personalized federated aggregation algorithm, named federated weighted proportion reduction (FedWPR), to tackle the problem of non-independent identically distribution caused by client diversity, thus achieving the best performance for each client. To thoroughly evaluate the effectiveness of FedFV, comprehensive experiments are conducted on nine publicly available finger vein datasets. Experimental results show that FedFV can improve the performance of the finger vein authentication system without directly using other client data. To the best of our knowledge, FedFV is the first personalized federated finger vein authentication framework, which has some reference value for subsequent biometric privacy protection research.

     

  • loading
  • [1]
    A. Uhl, C. Busch, S. Marcel, R. Veldhuis. Handbook of Vascular Biometrics, Cham, Switzerland: Springer, 2020. DOI: 10.1007/978-3-030-27731-4.
    [2]
    L. Y. Xu, Z. Gajic. Improved network for face recognition based on feature super resolution method. International Journal of Automation and Computing, vol. 18, no. 6, pp. 915–925, 2021. DOI: 10.1007/s11633-021-1309-9.
    [3]
    W. Jia, W. Xia, Y. Zhao, H. Min, Y. X. Chen. 2D and 3D palmprint and palm vein recognition based on neural architecture search. International Journal of Automation and Computing, vol. 18, no. 3, pp. 377–409, 2021. DOI: 10.1007/s11633-021-1292-1.
    [4]
    W. Jia, J. Gao, W. Xia, Y. Zhao, H. Min, J. T. Lu. A performance evaluation of classic convolutional neural networks for 2D and 3D palmprint and palm vein recognition. International Journal of Automation and Computing, vol. 18, no. 1, pp. 18–44, 2021. DOI: 10.1007/s11633-020-1257-9.
    [5]
    S. Tang, S. Zhou, W. X. Kang, Q. X. Wu, F. Q. Deng. Finger vein verification using a Siamese CNN. IET Biometrics, vol. 8, no. 5, pp. 306–315, 2019. DOI: 10.1049/iet-bmt.2018.5245.
    [6]
    N. Miura, A. Nagasaka, T. Miyatake. Extraction of finger-vein patterns using maximum curvature points in image profiles. Extraction of finger-vein patterns using maximum curvature points in image profiles. IEICE-TRANSACTIONS on Information and Systems, vol. E90-D, no. 8, pp. 1185–1194, 2007. DOI: 10.1093/ietisy/e90-d.8.1185.
    [7]
    W. Song, T. Kim, H. C. Kim, J. H. Choi, H. J. Kong, S. R. Lee. A finger-vein verification system using mean curvature. Pattern Recognition Letters, vol. 32, no. 11, pp. 1541–1547, 2011. DOI: 10.1016/j.patrec.2011.04.021.
    [8]
    W. M. Yang, Z. Q. Chen, C. Qin, Q. M. Liao. α-trimmed weber representation and cross section asymmetrical coding for human identification using finger images. IEEE Transactions on Information Forensics and Security, vol. 14, no. 1, pp. 90–101, 2018. DOI: 10.1109/TIFS.2018.2844803.
    [9]
    H. C. Lee, B. J. Kang, E. C. Lee, K. R. Park. Finger vein recognition using weighted local binary pattern code based on a support vector machine. Journal of Zhejiang University SCIENCE C, vol. 11, no. 7, pp. 514–524, 2010. DOI: 10.1631/jzus.C0910550.
    [10]
    Y. T. Lu, M. Tu, H. Wang, J. H. Zhao, W. X. Kang. Finger vein recognition based on double-orientation coding histogram. In Proceedings of the 14th Chinese Conference on Biometric Recognition, Springer, Zhuzhou, China, pp. 20–27, 2019. DOI: 10.1007/978-3-030-31456-9_3.
    [11]
    J. D. Wu, C. T. Liu. Finger-vein pattern identification using principal component analysis and the neural network technique. Expert Systems with Applications, vol. 38, no. 5, pp. 5423–5427, 2011. DOI: 10.1016/j.eswa.2010.10.013.
    [12]
    F. Liu, Y. L. Yin, G. P. Yang, L. M. Dong, X. M. Xi. Finger vein recognition with superpixel-based features. In Proceedings of IEEE International Joint Conference on Biometrics, Clearwater, USA, pp. 1–8, 2014. DOI: 10.1109/BTAS.2014.6996232.
    [13]
    L. Yang, G. P. Yang, X. M. Xi, K. Su, Q. Chen, Y. L. Yin. Finger vein code: From indexing to matching. IEEE Transactions on Information Forensics and Security, vol. 14, no. 5, pp. 1210–1223, 2019. DOI: 10.1109/TIFS.2018.2871778.
    [14]
    W. X. Kang, Y. T. Lu, D. J. Li, W. Jia. From noise to feature: Exploiting intensity distribution as a novel soft biometric trait for finger vein recognition. IEEE Transactions on Information Forensics and Security, vol. 14, no. 4, pp. 858–869, 2019. DOI: 10.1109/TIFS.2018.2866330.
    [15]
    Y. X. Fang, Q. X. Wu, W. X. Kang. A novel finger vein verification system based on two-stream convolutional network learning. Neurocomputing, vol. 290, pp. 100–107, 2018. DOI: 10.1016/j.neucom.2018.02.042.
    [16]
    C. H. Xie, A. Kumar. Finger vein identification using Convolutional Neural Network and supervised discrete hashing. Pattern Recognition Letters, vol. 119, pp. 148–156, 2019. DOI: 10.1016/j.patrec.2017.12.001.
    [17]
    H. C. Zheng, Y. J. Hu, B. B. Liu, G. Chen, A. C. Kot. A new efficient finger-vein verification based on lightweight neural network using multiple schemes. In Proceedings of the 29th International Conference on Artificial Neural Networks, Springer, Bratislava, Slovakia, pp. 748–758, 2020. DOI: 10.1007/978-3-030-61609-0_59.
    [18]
    Z. A. Hao, P. Y. Fang, H. W. Yang. Finger vein recognition based on multi-task learning. In Proceedings of the 5th International Conference on Mathematics and Artificial Intelligence, ACM, Chengdu, China, pp. 133–140, 2020. DOI: 10.1145/3395260.3395277.
    [19]
    J. D. Huang, M. Tu, W. L. Yang, W. X. Kang. Joint attention network for finger vein authentication. IEEE Transactions on Instrumentation and Measurement, vol. 70, Article number 2513911, 2021. DOI: 10.1109/TIM.2021.3109978.
    [20]
    R. S. Kuzu, E. Piciucco, E. Maiorana, P. Campisi. On-the-fly finger-vein-based biometric recognition using deep neural networks. IEEE Transactions on information Forensics and Security, vol. 15, pp. 2641–2654, 2020. DOI: 10.1109/TIFS.2020.2971144.
    [21]
    W. L. Yang, W. Luo, W. X. Kang, Z. X. Huang, Q. X. Wu. FVRAS-Net: An embedded finger-vein recognition and antiSpoofing system using a unified CNN. IEEE Transactions on Instrumentation and Measurement, vol. 69, no. 11, pp. 8690–8701, 2020. DOI: 10.1109/TIM.2020.3001410.
    [22]
    J. D. Huang, W. J. Luo, W. L. Yang, A. Zheng, F. Z. Lian, W. X. Kang. FVT: Finger vein transformer for authentication. IEEE Transactions on Instrumentation and Measurement, vol. 71, Article number 5011813, 2022. DOI: 10.1109/TIM.2022.3173276.
    [23]
    B. McMahan, E. Moore, D. Ramage, S. Hampson, B. A. Y. Arcas. Communication-efficient learning of deep networks from decentralized data. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, USA, pp. 1273–1282, 2017.
    [24]
    S. Ramaswamy, R. Mathews, K. Rao, F. Beaufays. Federated learning for emoji prediction in a mobile keyboard. [Online], Available: https://arxiv.org/abs/1906.04329, 2019.
    [25]
    T. Yang, G. Andrew, H. Eichner, H. C. Sun, W. Li, N. Kong, D. Ramage, F. Beaufays. Applied federated learning: Improving Google keyboard query suggestions. [Online], Available: https://arxiv.org/abs/1812.02903, 2018.
    [26]
    Y. Zhao, M. Li, L. Z. Lai, N. Suda, D. Civin, V. Chandra. Federated learning with non-ⅡD data. [Online], Available: https://arxiv.org/abs/1806.00582, 2018.
    [27]
    K. Hsieh, A. Phanishayee, O. Mutlu, P. Gibbons. The non-ⅡD data quagmire of decentralized machine learning. In Proceedings of the 37th International Conference on Machine Learning, pp. 4387–4398, 2020.
    [28]
    A. K. Sahu, T. Li, M. Sanjabi, M. Zaheer, A. Talwalkar, V. Smith. On the convergence of federated optimization in heterogeneous networks. [Online], Available: https://arxiv.org/abs/1812.06127v1, 2018.
    [29]
    F. Bai, J. X. Wu, P. C. Shen, S. X. Li, S. G. Zhou. Federated face recognition. [Online], Available: https://arxiv.org/abs/2105.02501, 2021.
    [30]
    Z. H. Tang, Z. K. Hu, S. H. Shi, Y. M. Cheung, Y. L. Jin, Z. H. Ren, X. W. Chu. Data resampling for federated learning with non-ⅡD labels. In Proceedings of the International Workshop on Federated and Transfer Learning for Data Sparsity and Confidentiality in Conjunction with IJCAI 2021, 2021.
    [31]
    A. Z. Tan, H. Yu, L. Z. Cui, Q. Yang. Towards personalized federated learning. IEEE Transactions on Neural Networks and Learning Systems, to be published. DOI: 10.1109/TNNLS.2022.3160699.
    [32]
    Y. Q. Chen, X. Qin, J. D. Wang, C. H. Yu, W. Gao. FedHealth: A federated transfer learning framework for wearable healthcare. IEEE Intelligent Systems, vol. 35, no. 4, pp. 83–93, 2020. DOI: 10.1109/MIS.2020.2988604.
    [33]
    W. M. Zhuang, Y. G. Wen, X. S. Zhang, X. Gan, D. Y. Yin, D. Z. Zhou, S. Zhang, S. Yi. Performance optimization of federated person re-identification via benchmark analysis. In Proceedings of the 28th ACM International Conference on Multimedia, ACM, Seattle, USA, pp. 955–963, 2020. DOI: 10.1145/3394171.3413814.
    [34]
    S. Itahara, T. Nishio, Y. Koda, M. Morikura, K. Yamamoto. Distillation-based semi-supervised federated learning for communication-efficient collaborative training with non-ⅡD private data. IEEE Transactions on Mobile Computing, to be published. DOI: 10.1109/TMC.2021.3070013.
    [35]
    V. Smith, C. K. Chiang, M. Sanjabi, A. Talwalkar. Federated multi-task learning. Proceedings of the 31st Conference on Neural Information Processing Systems, Long Beach, USA, pp. 4424–4434, 2017.
    [36]
    T. Li, S. Y. Hu, A. Beirami, V. Smith. Ditto: Fair and robust federated learning through personalization. In Proceedings of the 38th International Conference on Machine Learning, pp. 6357–6368, 2021.
    [37]
    T. Li, S. Y. Hu, A. Beirami, V. Smith. Ditto: Fair and robust federated learning through personalization. [Online], Available: https://arxiv.org/abs/2012.04221, 2020.
    [38]
    J. Li, M. Khodak, S. Caldas, A. Talwalkar. Differentially private meta-learning. [Online], Available: https://arxiv.org/abs/1909.05830, 2019.
    [39]
    F. Chen, M. Luo, Z. H. Dong, Z. G. Li, X. Q. He. Federated meta-learning with fast convergence and efficient communication. [Online], Available: https://arxiv.org/abs/1802.07876, 2018.
    [40]
    A. Fallah, A. Mokhtari, A. Ozdaglar. Personalized federated learning: A meta-learning approach. [Online], Available: https://arxiv.org/abs/2002.07948, 2020.
    [41]
    Y. H. Jiang, J. Konečnỳ, K. Rush, S. Kannan. Improving federated learning personalization via model agnostic meta learning. [Online], Available: https://arxiv.org/abs/1909.12488, 2019.
    [42]
    F. Sattler, K. R. Muller, W. Samek. Clustered federated learning: Model-agnostic distributed multitask optimization under privacy constraints. IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 8, pp. 3710–3722, 2021. DOI: 10.1109/TNNLS.2020.3015958.
    [43]
    L. Huang, A. L. Shea, H. N. Qian, A. Masurkar, H. Deng, D. B. Liu. Patient clustering improves efficiency of federated machine learning to predict mortality and hospital stay time using distributed electronic medical records. Journal of Biomedical Informatics, vol. 99, Article number 103291, 2019. DOI: 10.1016/j.jbi.2019.103291.
    [44]
    Y. T. Huang, L. Y. Chu, Z. R. Zhou, L. J. Wang, J. C. Liu, J. Pei, Y. Zhang. Personalized cross-silo federated learning on non-ⅡD data. In Proceedings of the 35th AAAI Conference on Artificial Intelligence, pp. 7865–7873, 2021.
    [45]
    Z. Chai, Y. J. Chen, L. Zhao, Y. Cheng, H. Rangwala. FedAT: A communication-efficient federated learning method with asynchronous tiers under non-ⅡD data. [Online], Available: https://arxiv.org/abs/2010.05958, 2020.
    [46]
    l. Masi, Y. Wu, T. Hassner, P. Natarajan. Deep face recognition: A survey. In Proceedings of the 31st SIBGRAPI Conference on Graphics, Patterns and Images, IEEE, Parana, Brazil, pp. 471478, 2018. DOI: 10.1109/SIBGRAPI.2018.00067.
    [47]
    M. Sandler, A. Howard, M. L. Zhu, A. Zhmoginov, L. C. Chen. MobileNetV2: Inverted residuals and linear bottlenecks. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Salt Lake City, USA, pp. 4510–4520, 2018. DOI: 10.1109/CVPR.2018.00474.
    [48]
    P. T. de Boer, D. P. Kroese, S. Mannor, R. Y. Rubinstein. A tutorial on the cross-entropy method. Annals of Operations Research, vol. 134, no. 1, pp. 19–67, 2005. DOI: 10.1007/s10479-005-5724-z.
    [49]
    Y. D. Wen, K. P. Zhang, Z. F. Li, Y. Qiao. A discriminative feature learning approach for deep face recognition. In Proceedings of the 14th European Conference on Computer Vision, Springer, Amsterdam, The Netherlands, pp. 499–515, 2016. DOI: 10.1007/978-3-319-46478-7_31.
    [50]
    Y. Lu, S. J. Xie, S. Yoon, Z. H. Wang, D. S. Park. An available database for the research of finger vein recognition. In Proceedings of the 6th International Congress on Image and Signal Processing, IEEE, Hangzhou, China, pp. 410–415, 2013. DOI: 10.1109/CISP.2013.6744030.
    [51]
    A. Kumar, Y. B. Zhou. Human identification using finger images. IEEE Transactions on Image Processing, vol. 21, no. 4, pp. 2228–2244, 2012. DOI: 10.1109/TIP.2011.2171697.
    [52]
    C. Kauba, B. Prommegger, A. Uhl. Focussing the beam - A new laser illumination based data set providing insights to finger-vein recognition. In Proceedings of the 9th International Conference on Biometrics Theory, Applications and Systems, IEEE, Redondo Beach, USA, pp. 1–9, 2018. DOI: 10.1109/BTAS.2018.8698588.
    [53]
    Y. L. Yin, L. L. Liu, X. W. Sun. SDUMLA-HMT: A multimodal biometric database. In Proceedings of the 6th Chinese Conference on Biometric Recognition, Springer, Beijing, China, pp. 260–268, 2011. DOI: 10.1007/978-3-642-25449-9_33.
    [54]
    W. M. Yang, C. Qin, Q. M. Liao. A database with ROI extraction for studying fusion of finger vein and finger dorsal texture. In Proceedings of the 9th Chinese Conference on Biometric Recognition, Springer, Shenyang, China, pp. 266–270, 2014. DOI: 10.1007/978-3-319-12484-1_30.
    [55]
    M. S. M. Asaari, S. A. Suandi, B. A. Rosdi. Fusion of band limited phase only correlation and width centroid contour distance for finger based biometrics. Expert Systems with Applications, vol. 41, no. 7, pp. 3367–3382, 2014. DOI: 10.1016/j.eswa.2013.11.033.
    [56]
    B. T. Ton, R. N. J. Veldhuis. A high quality finger vascular pattern dataset collected using a custom designed capturing device. In Proceedings of International Conference on Biometrics, IEEE, Madrid, Spain, 2013. DOI: 10.1109/ICB.2013.6612966.
    [57]
    P. Tome, M. Vanoni, S. Marcel. On the vulnerability of finger vein recognition to spoofing. In Proceedings of International Conference of the Biometrics Special Interest Group, IEEE, Darmstadt, Germany, pp. 111–120, 2014.
    [58]
    B. R. Hou, R. Q. Yan. ArcVein-arccosine center loss for finger vein verification. IEEE Transactions on Instrumentation and Measurement, vol. 70, Article number 5007411, 2021. DOI: 10.1109/TIM.2021.3062164.
    [59]
    H. F. Qin, M. A. El-Yacoubi. Deep representation-based feature extraction and recovering for finger-vein verification. IEEE Transactions on Information Forensics and Security, vol. 12, no. 8, pp. 1816–1829, 2017. DOI: 10.1109/TIFS.2017.2689724.
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(4)  / Tables(5)

    用微信扫码二维码

    分享至好友和朋友圈

    Article Metrics

    Article views (19) PDF downloads(0) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return