Skip to main content
SpringerLink
Log in

Vascular Enhancement Analysis in Lightweight Deep Feature Space

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

Finger-vein has been used for automatic personal recognition systems for over a decade. Its size and characteristics against presentation attacks make it suitable for various commercial and governmental applications. As with other biometric traits, the majority of finger-vein recognition methods employ hand-crafted feature for image classification. Lately, there are some convolutional neural network (CNN) models are designed for finger-vein identification and verification. Whereas, the CNN-based approaches tend to set up increasing layers and more parameters, which incur equipment memory issue and algorithm execution speed issue. Besides, many researchers have made great efforts to enhance hand-crafted feature-based method by using image enhancement algorithms. Hence, it is significant to explore high-performance finger-vein recognition without image enhancement in deep learning world. In this work, two different dimension issues are investigated: lightweight CNN model, the effect of image enhancement on finger-vein biometrics in deep feature space. Transfer learning plays an important role in extracting informative and representative features by information transfer from the pre-trained network to a novice via fine-tuning. The experimental results on four benchmark databases HKPU, FV-USM, SDUMLA and UTFVP demonstrate the proposed lightweight model ‘LightFVN’ outperforms the existing published competition winners. Furthermore, image enhancement turns out not to be essential for CNN-based finger-vein biometrics.

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

Access this article

Log in via an institution

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

Similar content being viewed by others

Notes

  1. http://www.cs.toronto.edu/~kriz/cifar.html.

References

  1. Kumar A, Zhou Y (2012) Human identification using finger images. IEEE Trans Image Process. 21(4):2228–2244

    Article  MathSciNet  MATH  Google Scholar 

  2. Menott D, Chiachia G, Pinto A, Schwartz W, Pedrini H, Falcao A et al (2015) Deep representations for iris, face, and fingerprint spoofing detection. IEEE Trans Inf Foren Sec. 10(4):864–879

    Article  Google Scholar 

  3. Noh KS (2016) A study on the authentication and security of financial settlement using the finger vein technology in wireless internet environment. Wireless Pers Commun. 89(3):761–775

    Article  Google Scholar 

  4. Zharov V, Ferguson S, Eidt J, Howard P, Fink L, Waner M (2004) Infrared imaging of subcutaneous veins. Lasers Surgery Med. 34(1):56–61

    Article  Google Scholar 

  5. Yang L, Yang G, Xi X, Su K, Chen Q, Yin Y (2019) Finger Vein Code: From Indexing to Matching. IEEE Trans Inf Foren Sec. 14(5):1210–1223

    Article  Google Scholar 

  6. Hu N, Ma H, Zhan T (2020) Finger vein biometric verification using block multi-scale uniform local binary pattern features and block two-directional twodimension principal component analysis. Optik. 208:1–10

    Article  Google Scholar 

  7. Meng X, Zheng J, Xi X, Zhang Q, Yin Y (2021) Finger vein recognition based on zone-based minutia matching. Neurocomputing. 423(5):110–123

    Article  Google Scholar 

  8. Xie C, Kumar A (2019) Finger vein identification using convolutional neural network and supervised discrete hashing. Pattern recognit lett. 119:148–156

    Article  Google Scholar 

  9. Zhao D, Ma H, Yang Z, Li J, Tian W (2020) Finger vein recognition based on lightweight CNN combining center loss and dynamic regularization. Infrared Phys Techn. 105:1–10

    Article  Google Scholar 

  10. Getreuer P (2012) Automatic color enhancement (ACE) and its fast implementation. Image Process On Line. 2:266–277

    Article  Google Scholar 

  11. Zuiderveld K (1994) Contrast Limited Adaptive Histogram Equalization. Graphic Gems IV, pp 474–485

  12. Asaari MSM, Suandi SA, Rosd BA (2014) Fusion of band limited phase only correlation and width centroid contour distance for finger based biometrics. Expert Syst Appl. 14(2):360–373

    Google Scholar 

  13. Yin Y, Liu L, Sun X (2011) SDUMLA-HMT: A multimodal biometric database. In: The 6th Chinese Conference on Biometric Recognition (CCBR 2011). 260–268

  14. Ton BT, Veldhuis RNJ (2013) A high quality finger vascular pattern dataset collected using a custom designed capturing device. In: Int. Conf. Biometrics (ICB). 1–5

  15. Syarif M, Ong T, Teoh A, Tee C (2017) Enhanced maximum curvature descriptors for finger vein verification. Multimed Tools Appl. 76:6859–6887

    Article  Google Scholar 

  16. Miura N, Nagasaka A, Miyatake T (2007) Extraction of finger-Vein patterns using maximum curvature points in image profiles. IEICE Trans Inf Syst. E90–D(8):1185–1194

    Article  Google Scholar 

  17. Wang J, Xiao J, Lin W, Luo C (2015) Discriminative and generative vocabulary tree: with application to vein image authentication and recognition. Image vis Comput. 34:51–62

    Article  Google Scholar 

  18. Zhu H, Chan F, Lam F (1999) Image contrast enhancement by constrained local histogram equalization. Comput vis image Und. 73(2):281–290

    Article  Google Scholar 

  19. Pizer S, Amburn E, Austin J, Cromartie R, Geselowitz A, Greer T et al (1987) Adaptive histogram equalization and its variations. Compt Vis Graph Image Process. 39:355–368

    Article  Google Scholar 

  20. Chikkerur S, Govindaraju V, Cartwright A (2005) Fingerprint image enhancement using STFT analysis. In: Int. Workshop Pattern Recognit. for Crime Prevent. Sec. Surveill. 20–29

  21. Lei L, Xi F, Chen S (2019) Finger-Vein image enhancement based on Pulse Coupled Neural Network. IEEE ACCESS. 7:57226–57237

    Article  Google Scholar 

  22. Das R, Piciucco E, Maiorana E, Campisi P (2019) Convolutional neural network for finger-vein-based biometric identification. IEEE Trans Inf Foren Sec. 14(2):360–373

    Article  Google Scholar 

  23. Ou W, Po L, Zhou C, Rehman YAU, Xian P (2021) Fusion loss and inter-class data augmentation for deep finger vein feature learning. Expert Syst Appl. 171:1–17

    Article  Google Scholar 

  24. Cai H, Gan C, Wang T, Zhang Z, Han S (2020) Once-for-All: Train One Network and Specialize it for Efficient Deployment. In: International Conference on Learning Representations (ICLR). 1–15

  25. Iandola F, Han S, Ashraf M, Dally K, Keutzer W (2017) Squeezenet: Alexnet-level accuracy with 50x fewer parameters and \(<0.5\)MB model size. In: Int. Conf. Learning Representations (ICLR). 1–13

  26. Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L (2018) MobileNetV2: Inverted residuals and linear bottlenecks. In: IEEE/CVF Conf. Comput. Vis. Pattern Recog. (CVPR). 4510–4520

  27. Howard A, Sandler M, Chu G, Chen L, Chen B, Tan M, et al (2019) Searching for MobileNetV3. In: IEEE/CVF Conf. Comput. Vis (ICCV). 1314–1324

  28. Ma N, Zhang X, Zheng H, Sun J (2018) ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design. In: European Comput. Vis (ECCV). 116–131

  29. Han K, Wang Y, Tian Q, Guo J, Xu C, Xu C (2020) GhostNet: More Features from Cheap Operations. In: IEEE/CVF Conf. Comput. Vis. Pattern Recog. (CVPR). 1580–1589

  30. Chen L, Wang J, Yang S, He H (2017) A finger vein image-based personal identification system with self-adaptive illuminance control. IEEE Trans Instrum Meas. 66(2):6859–6887

    Article  Google Scholar 

  31. Qin H, EI-Yacoubi MA (2018) Deep representation for finger-vein image-quality assessment. IEEE Tran Circuits Syst Video Technol. 28(8):1677–1693

    Article  Google Scholar 

  32. Kang Y, Chao G, Hu X, Tu Z, Chu D (2022) Deep Learning for Fine-Grained Image Recognition: A Comprehensive Study. In: Int. Conf. Comput. Vis. Computat. Intellig. 31–39

  33. Singh P, Prasad S, Chaudhary A, Patel C (2019) Classification of Effusion and Cartilage Erosion Affects in Osteoarthritis Knee MRI Images Using Deep Learning Model. In: Int. Conf. Comput. Vis. Image Process. 373–383

  34. Chao G, Luo Y, Ding W (2019) Recent Advances in Supervised Dimension Reduction: A Survey. Machine Learning and Knowledge Extraction. 1(1):341–358

    Article  Google Scholar 

  35. Lee EC, Lee HC, Park KR (2009) Finger vein recognition using minutia-based alignment and local binary pattern-based feature extraction. Int Journal of imag syst tech. 19(3):179–186

    Article  Google Scholar 

  36. Yang L, Yang G, Yin Y, Xiao R (2013) Sliding window-based region of interest extraction for finger vein images. Sensors. 13(3):3799–3815

    Article  Google Scholar 

  37. Yang J, Shi Y (2012) Finger-vein ROI localization and vein ridge enhancement. Pattern Recognit Lett. 33:1569–1579

    Article  Google Scholar 

  38. Deng J, Dong W, Socher R, Li L, Li K, Li F (2009) ImageNet: A large-scale hierarchical image database. In: IEEE Conf. Comput. Vis. Pattern Recognit.(CVPR). 248–255

  39. Gatta C, Rizzi A, Marini D (2002) ACE: An automatic color equalization algorithm. In: Int. Conf. Color in Graph. Image Vis. 1–6

  40. Liu H, Yang L, Yang G, Yin Y (2017) Discriminative Binary Descriptor for finger-vein recognition. IEEE Access 6:5795–5804

    Article  Google Scholar 

  41. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al (2015) Going deeper with convolutions. In: IEEE Conf. Comput. Vis. Pattern Recognit.(CVPR). 1–9

  42. Huang G, Zhuang L, Maaten L (2017) Densely Connected Convolutional Networks. In: IEEE Conf. Comput. Vis. Pattern Recognit.(CVPR). 1–9

Download references

Acknowledgements

The authors would like to thank The Hong Kong Polytechnic University, Universiti Sains Malaysia, Shandong University and The University of Twente for sharing the finger-vein databases. This work is supported by Young Teacher Development Fund of Harbin Institute of Technology (Grant No. IDGA10002081) and National Science Research Project of Department of Education in Guizhou Province (Grant No. KY[2020]112).

Author information

Author notes

  1. All authors contribute equally.

Authors and Affiliations

  1. Faculty of Computing, Harbin Institute of Technology, Harbin, 150001, People’s Republic of China

    Tingting Chai, Jiahui Li, Guoying Sun, Changyong Guo & Zhaoxin Zhang

  2. School of Communication, Tianjin Foreign Studies University, Tianjin, 300204, People’s Republic of China

    Yanhong Wang

Authors
  1. Tingting Chai
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jiahui Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yanhong Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Guoying Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Changyong Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Zhaoxin Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Changyong Guo.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chai, T., Li, J., Wang, Y. et al. Vascular Enhancement Analysis in Lightweight Deep Feature Space. Neural Process Lett 55, 2305–2320 (2023). https://doi.org/10.1007/s11063-022-10937-z

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-022-10937-z

Keywords

Search

Navigation