Skip to main content

Advertisement

Springer Nature Link
Log in

A finger vein feature extraction network fusing global/local features and its lightweight network

  • Original Paper
  • Published:
Evolving Systems Aims and scope Submit manuscript

Abstract

Finger vein recognition technology has been widely used in various identity authentication scenarios due to its convenience, fast recognition speed, and high security. However, there is an inevitable problem that seriously affects its recognition, which is the change of finger poses, such as shift and rotation during the image acquisition process. Therefore, how to extract finger vein features that are more robust to finger pose changes is a more concerned issue. We analyze the multi-pose finger vein images in practical application scenarios, and find the fact that the global vein features of the same finger are quite different while the local features are highly similar. In most existing finger vein recognition algorithms based on convolutional neural network (CNN), only global finger vein features are extracted by global average pooling (GAP), which fails to take full account of the above fact. In this paper, we proposed a finger vein feature extraction network fusing global and local features (FGL-Net) and its lightweight network KD-FGL-MobileNet, which effectively improves finger vein recognition performance in different finger poses. Firstly, FGL-Net consists of two parts, the backbone network based on the designed ResBlock with Mish is used to extract the high-level semantic features of finger veins, and then the global and local feature extraction module with three independent branches are designed to fully learn the global and local finger vein features at different granularities, and finally all the features of the three branches are fused into a fusion feature with greater robustness to pose change for recognition. To improve the generalization ability of the network, the CurricularFace loss is added to train FGL-Net with the cross-entropy loss. Such design not only aggregates homologous features and separates heterologous features, but also mines finger vein image samples under special poses online for intensive training. Secondly, according to the characteristics of the finger veins, we design a lightweight residual block based on fast receptive field (SE-FrfResBlock) to build a more lightweight FGL-MobileNet. A knowledge distillation loss and a feature map loss are added to FGL-MobileNet to address the generalization performance degradation of FGL-MobileNet, and we named it KD-FGL-MobileNet. On FV-USM, FV-Normal and FV-Specical datasets, compared with VGG-Net and InceptionResnet, the Top1 ranking of FGL-Net are improved by 2.38%, 8.26%, 13.42% and 0.00%, 1.17%, 9.95%, and the recognition rate are improved by 9.42%, 18.59%, 28.33% and 0.72%, 7.12%, 20.88%. On FV-Specical datasets, compared with MobileNetv3, FGL-MobileNet, the recognition rate and Top1 ranking of KD-FGL-MobileNet are improved by 24.12% ,6.19% and 12.46%, 3.78%. The above results show that the proposed FGL-Net effectively improves the recognition performance of finger vein images in different poses, and KD-FGL-MobileNe requires less storage space while remaining basically consistent with the performance of FGL-Net.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Explore related subjects

Discover the latest articles and news from researchers in related subjects, suggested using machine learning.

Data availability

The datasets of this paper consists of three parts: FV-USM dataset that support the findings of this study is available in [Finger Vein USM Database] with the identifier http://dx.doi.org/10.1016/j.eswa.2013.11.033] Asaari et al. (2014), FV-Normal and FV-Special datasets are not available due to trade secrets. No known interest that can influence the work reported in this paper.

References

  • Abualigah L, Diabat A, Mirjalili S, Abd Elaziz M, Gandomi AH (2021) The arithmetic optimization algorithm. Comput Methods Appl Mech Eng 376:113609

    Article  MathSciNet  MATH  Google Scholar 

  • Abualigah L, Diabat A, Sumari P, Gandomi AH (2021) Applications, deployments, and integration of internet of drones (IoD): a review. IEEE Sens J 21(22):25532–25546

    Article  Google Scholar 

  • Abualigah L, Yousri D, Abd Elaziz M, Ewees AA, Al-Qaness MA, Gandomi AH (2021) Aquila optimizer: a novel meta-heuristic optimization algorithm. Comput Ind Eng 157:107250

    Article  Google Scholar 

  • Abualigah L, Abd Elaziz M, Sumari P, Geem ZW, Gandomi AH (2022) Reptile search algorithm (RSA): a nature-inspired meta-heuristic optimizer. Expert Syst Appl 191:116158

    Article  Google Scholar 

  • Agushaka JO, Ezugwu AE, Abualigah L (2022) Dwarf mongoose optimization algorithm. Comput Methods Appl Mech Eng 391:114570

    Article  MathSciNet  MATH  Google Scholar 

  • Asaari MSM, Suandi SA, Rosdi BA (2014) Fusion of band limited phase only correlation and width centroid contour distance for finger based biometrics. Expert Syst Appl 41(7):3367–3382

    Article  Google Scholar 

  • Clevert D-A, Unterthiner T, Hochreiter S (2015) Fast and accurate deep network learning by exponential linear units (ELUS). arXiv:1511.07289 (arXiv preprint)

  • Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, pp 315–323

  • Hinton G, Vinyals O, Dean J (2015) Distilling the knowledge in a neural network. Comput Sci 14(7):38–39

    Google Scholar 

  • Hong HG, Lee MB, Park KR (2017) Convolutional neural network-based finger-vein recognition using NIR image sensors. Sensors 17(6):1297

    Article  Google Scholar 

  • Howard A, Sandler M, Chu G, Chen L-C, Chen B, Tan M, Wang W, Zhu Y, Pang R, Vasudevan V, et al. (2019) Searching for mobilenetv3. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 1314–1324

  • Huang Y, Wang Y, Tai Y, Liu X, Shen P, Li S, Li J, Huang F (2020) Curricularface: adaptive curriculum learning loss for deep face recognition. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 5901–5910

  • Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132–7141

  • Ismail B, Zmirli MO (2018) Enhancement of finger vein patterns extracted by maximum curvature method. In: 2018 international conference on applied smart systems (ICASS), pp 1–4. IEEE

  • Itqan K, Syafeeza A, Gong F, Mustafa N, Wong Y, Ibrahim M (2016) User identification system based on finger-vein patterns using convolutional neural network. ARPN J Eng Appl Sci 11(5):3316–3319

    Google Scholar 

  • Kang BJ, Park KR (2010) Multimodal biometric method based on vein and geometry of a single finger. IET Comput Vis 4(3):209–217

    Article  Google Scholar 

  • Khellat-Kihel S, Cardoso N, Monteiro J, Benyettou M, et al. (2014) Finger vein recognition using gabor filter and support vector machine. In: International image processing, applications and systems conference, pp 1–6. IEEE

  • Li J, Ma H, Lv Y, Zhao D, Liu Y (2019) Finger vein feature extraction based on improved maximum curvature description. In: 2019 Chinese control conference (CCC), pp 7566–7571. IEEE

  • Liu T, Xie J, Yan W, Li P, Lu H (2013) An algorithm for finger-vein segmentation based on modified repeated line tracking. Imaging Sci J 61(6):491–502

    Article  Google Scholar 

  • Liu F, Yang G, Yin Y, Wang S (2014) Singular value decomposition based minutiae matching method for finger vein recognition. Neurocomputing 145:75–89

    Article  Google Scholar 

  • Liu W, Li W, Sun L, Zhang L, Chen P (2017) Finger vein recognition based on deep learning. In: 2017 12th IEEE conference on industrial electronics and applications (ICIEA), pp 205–210. IEEE

  • Lu Y, Yoon S, Xie SJ, Yang J, Wang Z, Park DS (2014) Finger vein recognition using generalized local line binary pattern. KSII Trans Internet Inf Syst 8(5):1766–1784

    Google Scholar 

  • Lu Y, Xie SJ, Yoon S, Park DS (2013) Finger vein identification using polydirectional local line binary pattern. In: 2013 international conference on ICT convergence (ICTC), pp 61–65. IEEE

  • Maas AL, Hannun AY, Ng AY, et al. (2013) Rectifier nonlinearities improve neural network acoustic models. In: Proceedings of ICML, vol 30, p 3. Citeseer

  • Mantrao N, Sukhpreet K (2015) An efficient minutiae matching method for finger vein recognition. Int J Adv Res Comput Sci Softw Eng 5:657–660

    Google Scholar 

  • Meng X, Zheng J, Xi X, Zhang Q, Yin Y (2021) Finger vein recognition based on zone-based minutia matching. Neurocomputing 423:110–123

    Article  Google Scholar 

  • Mish MD (2019) A self regularized non-monotonic activation function 2019. arXiv:1908.08681 (arXiv preprint)

  • Miura N, Nagasaka A, Miyatake T (2004) Feature extraction of finger-vein patterns based on repeated line tracking and its application to personal identification. Mach Vis Appl 15(4):194–203

    Article  Google Scholar 

  • Miura N, Nagasaka A, Miyatake T (2007) Extraction of finger-vein patterns using maximum curvature points in image profiles. IEICE Trans Inf Syst 90(8):1185–1194

    Article  Google Scholar 

  • Oyelade ON, Ezugwu AE-S, Mohamed TI, Abualigah L (2022) Ebola optimization search algorithm: a new nature-inspired metaheuristic optimization algorithm. IEEE Access 10:16150–16177

    Article  Google Scholar 

  • Prabhakar P, Thomas T (2013) Finger vein identification based on minutiae feature extraction with spurious minutiae removal. In: 2013 third international conference on advances in computing and communications, pp 196–199

  • Radzi SA, Hani MK, Bakhteri R (2016) Finger-vein biometric identification using convolutional neural network. Turk J Electr Eng Comput Sci 24(3):1863–1878

    Article  Google Scholar 

  • Rosdi BA, Shing CW, Suandi SA (2011) Finger vein recognition using local line binary pattern. Sensors 11(12):11357–11371

    Article  Google Scholar 

  • Song W, Kim T, Kim HC, Choi JH, Kong H-J, Lee S-R (2011) A finger-vein verification system using mean curvature. Pattern Recogn Lett 32(11):1541–1547

    Article  Google Scholar 

  • Syarif MA, Ong TS, Teoh AB, Tee C (2017) Enhanced maximum curvature descriptors for finger vein verification. Multimed Tools Appl 76(5):6859–6887

    Article  Google Scholar 

  • Szegedy C, Ioffe S, Vanhoucke V, Alemi AA (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In: Thirty-first AAAI conference on artificial intelligence

  • Wang X, Wang H, He Y, Ding Y, Tao L (2019b) Novel algorithm for finger vein recognition based on inception-resnet module. In: Eleventh international conference on digital image processing (ICDIP 2019), vol 11179, p 111791D. International Society for Optics and Photonics

  • Wu J, He D (2018) Finger vein recognition based on feature point distance. In: 2018 IEEE 3rd international conference on image, vision and computing (ICIVC), pp 163–167. IEEE

  • Yang J, Yang J (2009) Multi-channel gabor filter design for finger-vein image enhancement. In: 2009 fifth international conference on image and graphics, pp 87–91. IEEE

  • Yang J, Yang J, Shi Y (2009) Combination of gabor wavelets and circular gabor filter for finger-vein extraction. In: International conference on intelligent computing, pp 346–354. Springer

  • Zhang Y, Li W, Zhang L, Lu Y (2019) Adaptive gabor convolutional neural networks for finger-vein recognition. In: 2019 international conference on high performance big data and intelligent systems (HPBD &IS), pp 219–222. IEEE

Download references

Author information

Authors and Affiliations

  1. College of Communication Engineering, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China

    Wengui Xu & Lei Shen

  2. College of Engineering, Architecture and Technology (CEAT), Oklahoma State University, Stillwater, OK, 74078, USA

    Huaxia Wang

  3. Stevens Institute of Technology, Hoboken, NJ, 07030, USA

    Yudong Yao

Authors
  1. Wengui Xu
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Lei Shen
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Huaxia Wang
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Yudong Yao
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Lei Shen.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xu, W., Shen, L., Wang, H. et al. A finger vein feature extraction network fusing global/local features and its lightweight network. Evolving Systems 14, 873–889 (2023). https://doi.org/10.1007/s12530-022-09475-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12530-022-09475-9

Keywords