Skip to main content
SpringerLink
Log in

Multi-task Pre-training with Soft Biometrics for Transfer-learning Palmprint Recognition

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

As a discriminative biometric modality, palmprint accommodates two attributes of soft biometrics, namely chirality and gender. Our study reveals that the false matching of a pair of palmprint templates from two identities could be possible if their representations are mirror-insensitive or gender-insensitive, despite the palmprint images have significant distinctive appearances. This could seriously impair the accuracy performance of the palmprint recognition systems. As a remedy, the useful knowledge learned from the classification of soft palmprint attributes, namely chirality and gender, is transferred to palmprint recognition, which improves the accuracy of palmprint-based identity recognition. To be specific, this paper pre-trains a shared-weight multi-task network with soft palmprint attributes under transfer learning paradigm. The pre-trained network is then transferred to the down-stream identity recognition task. Several shared-weight architectures are explored and examined to determine the suitable model. Extensive experiments demonstrate that the proposed method can effectively avoid the false matching between the templates of different chiralities / genders. The proposed method can be applied to other biometric modalities, where their associated soft biometrics can be exploited for performance gain. The related codes will be released as soon as possible if the paper is accepted. The link is https://github.com/1119231393/Multi-task-Pre-training-with-Soft-Biometrics-for-Transfer-learning-Palmprint-Recognition.

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
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. Jasmine RM, Jasper J (2021) A privacy preserving based multi-biometric system for secure identification in cloud environment. Neural Process Lett. https://doi.org/10.1007/s11063-021-10630-7

    Article  Google Scholar 

  2. Zhou D, Yang D, Zhang X et al (2019) Discriminative probabilistic latent semantic analysis with application to single sample face recognition. Neural Process Lett 49(3):1273–1298. https://doi.org/10.1007/s11063-018-9852-2

    Article  Google Scholar 

  3. Fei L, Lu G, Jia W et al (2019) Feature extraction methods for palmprint recognition: a survey and evaluation. IEEE Trans Syst, Man, Cybernet: Syst 49(2):346–363

    Article  Google Scholar 

  4. Joshi D, Mishra V, Srivastav H et al (2021) Progressive transfer learning approach for identifying the leaf type by optimizing network parameters. Neural Process Lett. https://doi.org/10.1007/s11063-021-10521-x

    Article  Google Scholar 

  5. Banos O, Calatroni A, Damas M et al (2021) Opportunistic activity recognition in iot sensor ecosystems via multimodal transfer learning. Neural Process Lett. https://doi.org/10.1007/s11063-021-10468-z

    Article  Google Scholar 

  6. Ungureanu A, Salahuddin S, Corcoran P (2020) Towards unconstrained palmprint recognition on consumer devices: a literature review. IEEE Access 8:86130–86148

    Article  Google Scholar 

  7. Zhong D, Du X, Zhong K (2018) Decade progress of palmprint recognition: a brief survey. Neurocomputing 328:16–28

    Article  Google Scholar 

  8. Chen P, Ding B, Wang H et al (2019) Design of low-cost personal identification system that uses combined palm vein and palmprint biometric features. IEEE Access 7:15922–15931

    Article  Google Scholar 

  9. Palma D, Montessoro PL, Giordano G et al (2017) Biometric palmprint verification: a dynamical system approach. IEEE Trans Syst, Man, Cybernet: Syst 49(12):2168–2216

    Google Scholar 

  10. Leng L, Zhang J (2013) PalmHash code vs. PalmPhasor code. Neurocomputing 108:1–12

    Article  Google Scholar 

  11. Fei L, Zhang B, Jia W et al (2020) Feature extraction for 3-D palmprint recognition: a survey. IEEE Trans Instrum Meas 69(3):645–656

    Article  Google Scholar 

  12. Fei L, Zhang B, Xu Y et al (2019) Precision direction and compact surface type representation for 3D palmprint identification. Pattern Recogn 87:237–247

    Article  Google Scholar 

  13. Lu L, Zhang X, Xu X (2019) Hypercomplex extreme learning machine with its application in multispectral palmprint recognition. PLoS ONE 14(4):1–18

    Article  Google Scholar 

  14. Hong D, Liu W, Su J et al (2015) A novel hierarchical approach for multispectral palmprint recognition. Neurocomputing 151:511–521

    Article  Google Scholar 

  15. Leng L, Gao F, Cheng Q et al (2018) Palmprint recognition system on mobile devices with double-line-single-point assistance. Pers Ubiquit Comput 22(1):93–104

    Article  Google Scholar 

  16. Xiao Q, Lu J, Jia W et al (2019) Extracting palmprint ROI from whole hand image using straight line clusters. IEEE Access 7:74327–74339

    Article  Google Scholar 

  17. Leng L, Teoh A (2015) Alignment-free row-co-occurrence cancelable palmprint fuzzy vault. Pattern Recognit: J Pattern Recognit Soc 48(7):2290–2303

    Article  Google Scholar 

  18. Leng L, Zhang J, Khan K et al (2010) Dynamic weighted discrimination power analysis: a novel approach for face and palmprint recognition in DCT domain. Int J Phys Sci 5(17):2543–2554

    Google Scholar 

  19. Rida I, AI-Maadeed S, Mahmood A et al (2018) Palmprint identification using an ensemble of sparse representations. IEEE Access 6:3241–3248

    Article  Google Scholar 

  20. Leng L, Zhang J, Chen G et al (2011) Two-directional two-dimensional random projection and its variations for face and palmprint recognition. Comput Sci Appl - ICCSA 2011:458–470

    Google Scholar 

  21. Fei L, Wen J, Zhang Z et al (2016) Local multiple directional pattern of palmprint image. In: International Conference on Pattern Recognition, pp. 3013–3018

  22. Yang Z, Leng L, Min W (2021) Extreme downsampling and joint feature for coding-based palmprint recognition. IEEE Trans Instrum Meas 70:1–12

    Article  Google Scholar 

  23. Leng L, Yang Z, Min W et al (2020) Democratic voting downsampling for coding-based palmprint recognition. IET Biometrics 9(6):290–296

    Article  Google Scholar 

  24. Genovese A, Piuri V, Plataniotis KN et al (2019) PalmNet: Gabor-PCA convolutional networks for touchless palmprint recognition. IEEE Trans Inf Forensics Secur 14(12):3160–3174

    Article  Google Scholar 

  25. Zhong D, Zhu J (2020) Centralized large margin cosine loss for open-set deep palmprint recognition. IEEE Trans Circuits Syst Video Technol 30(6):1559–1568

    Article  Google Scholar 

  26. Matkowski WM, Chai T, Kong A (2019) Palmprint recognition in uncontrolled and uncooperative environment. IEEE Trans Inf Forensics Secur 15:1601–1615

    Article  Google Scholar 

  27. Zhao S, Zhang B (2019) Deep discriminative representation for generic palmprint recognition. Pattern Recogn 98:107071

    Article  Google Scholar 

  28. Zhao S and Zhang B (2020) Joint constrained least-square regression with deep convolutional feature for palmprint recognition. IEEE Transactions on Systems, Man, and Cybernetics: Systems, pp 1–12

  29. Zhao S, Zhang B, Chen CP (2019) Joint deep convolutional feature representation for hyperspectral palmprint recognition. Inf Sci 489:167–181

    Article  MathSciNet  Google Scholar 

  30. Xie Z, Guo Z, Qian C (2018) Palmprint gender classification by convolutional neural network. IET Comput Vision 12(4):476–483

    Article  Google Scholar 

  31. Wu M, Yuan Y (2014) Gender classification based on geometry features of palm image. Sci World J 2014(2):734564–734564

    Google Scholar 

  32. Antipov G, Berrani S, Dugelay J (2016) Minimalistic CNN-based ensemble model for gender prediction from face images. Pattern Recogn Lett 70:59–65

    Article  Google Scholar 

  33. Levi G and Hassncer T (2015) Age and gender classification using convolutional neural networks. Computer Vision Pattern Recognition(CVPR), pp 34–42

  34. Zhang C, Ding H, Shang Y et al (2018) Gender classification based on multiscale facial fusion feature. Math Probl Eng 2018:1–6

    Google Scholar 

  35. Hurwitz E, Hasan AN, Orji C (2017) Soft biometrics thermal face recognition using FWT and LDA feature extraction method with RBM DBN and FFNN classifier algorithms. Int Conf Image Inf Process (ICIIP) 2017:1–6

    Google Scholar 

  36. Tome P, Vera-Rodriguez R, Fierrez J et al (2015) Facial soft biometrics for forensic face recognition. Forensic Sci Int 257:271–284

    Article  Google Scholar 

  37. Chai T, Prasad S, Wang S (2019) Boosting palmprint identity with gender information using DeepNet. Futur Gener Comput Syst 99:41–53

    Article  Google Scholar 

  38. Arigbabu OA, Ahmad SMS, Adnan WAW et al (2015) Integration of multiple soft biometrics for human identity. Pattern Recogn Lett 68:278–287

    Article  Google Scholar 

  39. Yang L, Yang G, Yin Y et al (2014) Exploring soft biometrics trait with finger vein recognition. Neurocomputing 135:218–228

    Article  Google Scholar 

  40. Almudhahka NY, Nixon MS, Hare JS (2018) Comparative Face Soft Biometrics for Human Identification. In: Karampelas P, Bourlai T (eds) Surveillance in Action. Springer, Cham, pp 25–50. https://doi.org/10.1007/978-3-319-68533-5_2

    Chapter  Google Scholar 

  41. Reid D, Nixon M, Stevenage S (2014) Soft biometrics: human identity using comparative descriptions. IEEE Trans Pattern Anal Mach Intell 36(6):1216–1228

    Article  Google Scholar 

  42. Kang W, Lu Y, Li D et al (2019) From noise to feature: exploiting intensity distribution as a novel soft biometrics trait for finger vein recognition. IEEE Trans Inf Forensics Secur 14(4):858–869

    Article  Google Scholar 

  43. Jain AK, Nandakumar K, Xiaoguang L, Park U (2004) Integrating faces, fingerprints, and soft biometric traits for user recognition. In: Maltoni D, Jain AK (eds) Biometric Authentication. Springer, Berlin, Heidelberg, pp 259–269. https://doi.org/10.1007/978-3-540-25976-3_24

    Chapter  Google Scholar 

  44. Jain AK and Park U (2009) Facial marks: soft biometrics for face recognition. International Conference on Image Processing(ICIP), pp. 37–40

  45. Tsinghua IC-LAB Palm_ROI_Gender_Database. Available: https://github.com/IC-LAB/Paml_ROI_Gender_Database

  46. Tongji palmprint image database. Available: https://cslinzhang.github.io/ContactlessPalm/

  47. PolyU Palmprint Database (Version 2.0). Available: https://www.comp.polyu.edu.hk/~biometrics

  48. CIFAR-10. Available: http://www.cs.toronto.edu/~kriz/cifar.html

  49. Zhou B, Khosla A, Lapedriza A et al (2016) Learning deep features for discriminative localization. IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921–2929

Download references

Acknowledgements

This research was funded by the National Natural Science Foundation of China (61866028), Technology Innovation Guidance Program Project (Special Project of Technology Cooperation, Science and Technology Department of Jiangxi Province) (20212BDH81003), and Open Foundation of Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition (ET201680245, TX201604002).

Author information

Authors and Affiliations

  1. Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition, Nanchang Hangkong University, Nanchang, 330063, People’s Republic of China

    Huanhuan Xu, Lu Leng & Zhe Jin

  2. College of Computer Science, Sichuan University, Chengdu, 610065, People’s Republic of China

    Ziyuan Yang

  3. School of Electrical and Electronic Engineering, College of Engineering, Yonsei University, Seoul, 120749, Republic of Korea

    Lu Leng & Andrew Beng Jin Teoh

  4. School of Artificial Intelligence, Anhui University, Heifei, 230039, People’s Republic of China

    Zhe Jin

Authors
  1. Huanhuan Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lu Leng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ziyuan Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Andrew Beng Jin Teoh
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zhe Jin
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Lu Leng.

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

Xu, H., Leng, L., Yang, Z. et al. Multi-task Pre-training with Soft Biometrics for Transfer-learning Palmprint Recognition. Neural Process Lett 55, 2341–2358 (2023). https://doi.org/10.1007/s11063-022-10822-9

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-022-10822-9

Keywords

Search

Navigation