Skip to main content
SpringerLink
Log in

Ordinal regression with representative feature strengthening for face anti-spoofing

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Face anti-spoofing is a crucial link to ensure the security of face recognition. This paper proposes a novel face anti-spoofing method, which performs ordinal regression with representative feature strengthening to learn generalized and discriminative representation for the live and spoof face classification. Specifically, we propose a semantic label schema, which encodes the inter-class ordinal relationships among live and various spoof faces into supervision information to supervise deep neural networks to perform ordinal regression. It enables the learned model to finely constrain the relative distances among features of different categories in the feature space according to the ordinal relationships. The representative feature strengthening network is designed to strengthen important features and meanwhile weaken redundant features for the classification decision. It leverages a dual-task architecture that takes the same single image as input and shares representations via feature fusing blocks. The network first fuses hierarchical paired convolutional features of two streams to learn the common concern of the two related tasks and then, aggregates the learned local convolutional features into a global representation by a learnable feature weighting block. The network is trained to minimize the Kullback–Leibler divergence loss in an end-to-end manner supervised by the semantic labels. Extensive intra-dataset and cross-dataset experiments demonstrate that the proposed method outperforms the state-of-the-art approaches on four widely used face anti-spoofing datasets.

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

Similar content being viewed by others

References

  1. Arandjelovic R, Gronat P, Torii A, Pajdla T, Sivic J (2016) In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5297–5307

  2. Atoum Y, Liu Y, Jourabloo A, Liu X (2017) In: 2017 IEEE International Joint Conference on Biometrics, IEEE. pp 319–328

  3. Bao W, Li H, Li N, Jiang W (2009) In: 2009 International Conference on Image Analysis and Signal Processing, IEEE, pp 233–236

  4. Benlamoudi A (2017) Face antispoofing based on frame difference and multilevel representation. J Electron Imaging 26(4):043007

    Article  Google Scholar 

  5. Biometrics IJS (2016) Information technology – biometric presentation attack detection – part 1: Framework. International Organization for Standardization 2

  6. Boulkenafet Z, Komulainen J, Hadid A (2016) Face spoofing detection using colour texture analysis. IEEE Trans Inf Forensics Secur 11(8):1818–1830

    Article  Google Scholar 

  7. Boulkenafet Z, Komulainen J, Hadid A (2017) Face antispoofing using speeded-up robust features and fisher vector encoding. IEEE Signal Process Lett 24(2):141–145

    Google Scholar 

  8. Boulkenafet Z, Hadid A (2015) In: 2015 IEEE international conference on image processing (ICIP). IEEE, pp 2636–2640

  9. Boulkenafet Z, Komulainen J, et al (2017) In: 2017 IEEE International Joint Conference on Biometrics (IJCB). IEEE, pp 688–696

  10. Boulkenafet Z, Komulainen J, Li L, Feng X, Hadid A (2017) In: 2017 12th IEEE International Conference on Automatic Face and Gesture Recognition. IEEE, pp 612–618

  11. Boureau YL, Ponce J, LeCun Y (2010) In: Proceedings of the 27th international conference on machine learning (ICML-10), pp 111–118

  12. Cai R, Li H, Wang S, Chen C, Kot AC (2020) Drl-fas: A novel framework based on deep reinforcement learning for face anti-spoofing. IEEE Trans Inf Forensics Secur 16:937–951

    Article  Google Scholar 

  13. Chen H, Hu G, Lei Z, Chen Y, Robertson NM, Li SZ (2019) Attention-based two-stream convolutional networks for face spoofing detection. IEEE Trans Inf Forensics Secur 15:578–593

    Article  Google Scholar 

  14. Chen S, Zhang C, Dong M, Le J, Rao M (2017) In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 5183–5192

  15. Chingovska I, Anjos A, Marcel S (2012) In: Proceedings of the 11th International Conference of the Biometrics Special Interes Group, EPFL-CONF-192369

  16. Cover TM (1999) Elements of information theory. John Wiley & Sons, New Jersey

    Google Scholar 

  17. de Freitas Pereira (2013) In: 2013 International Conference on Biometrics (ICB). IEEE, pp 1–8

  18. Deb D, Jain AK (2020) Look locally infer globally: A generalizable face anti-spoofing approach. arXiv preprint arXiv:2006.02834

  19. Duchi J, Hazan E, Singer Y (2011) Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res 12(Jul):2121–2159

    MathSciNet  MATH  Google Scholar 

  20. Feng L, Po LM, Li Y, Xu X, Yuan F, Cheung TCH, Cheung KW (2016) Integration of image quality and motion cues for face anti-spoofing: A neural network approach. J Vis Commun Image Represent 38:451–460

    Article  Google Scholar 

  21. Feng Y, Wu F, Shao X, Wang Y, Zhou X (2018) In: Proceedings of the European Conference on Computer Vision (ECCV), pp 534–551

  22. Fu H, Gong M, Wang C, Batmanghelich K, Tao D (2018) In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2002–2011

  23. Gan J, Li S, Zhai Y, Liu C (2017) In: 2017 2nd International Conference on Multimedia and Image Processing (ICMIP), IEEE, pp 1–5

  24. George A, Marcel S (2019) In: 2019 International Conference on Biometrics (ICB). IEEE, pp 1–8

  25. Granger E, Cardinal P, et al (2020) Deep da for ordinal regression of pain intensity estimation using weakly-labeled videos. arXiv preprint arXiv:2010.15675

  26. Guo J, Zhu X, Xiao J, Lei Z, Wan G, Li SZ (2019) In: 2019 International Conference on Biometrics (ICB). IEEE, pp 1–8

  27. Y.Z.L.C.X.X.J.Z.J.S.F.Y.W. Haiping Zhu, Hongming Shan (2020) Convolutional ordinal regression forest for image ordinal estimation. arXiv preprint arXiv:2008.03077

  28. He K, Zhang X, Ren S, Sun J (2016) In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778

  29. Huang Y, Zhang W, Wang J (2020) Deep frequent spatial temporal learning for face anti-spoofing. arXiv preprint arXiv:2002.03723

  30. Jia S, Li X, Hu C, Guo G, Xu Z (2020) 3d face anti-spoofing with factorized bilinear coding. arXiv preprint arXiv:2005.06514

  31. Jiang F, Liu P, Zhou X (2019) Multilevel fusing paired visible light and near-infrared spectral images for face anti-spoofing. Pattern Recogn Lett 128:30–37

    Article  Google Scholar 

  32. Jourabloo A, Liu Y, Liu X (2018) Face de-spoofing: Anti-spoofing via noise modeling. arXiv preprint arXiv:1807.09968

  33. Kim T, Kim Y, Kim I, Kim D (2019) In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp 0–0

  34. Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980

  35. Kollreider K, Fronthaler H, Bigun J (2009) Non-intrusive liveness detection by face images. Image Vis Comput 27(3):233–244

    Article  Google Scholar 

  36. LeCun Y, Bottou L, Bengio Y, Haffner P et al (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324

    Article  Google Scholar 

  37. Li H, He P, Wang S, Rocha A, Jiang X, Kot AC (2018) Learning generalized deep feature representation for face anti-spoofing. IEEE Trans Inf Forensics Secur 13(10):2639–2652

    Article  Google Scholar 

  38. Li H, Li W, Kot AC (2018) Unsupervised domain adaptation for face anti-spoofing. IEEE Trans Inf Forensics Secur 13(7):1794–1809

    Article  Google Scholar 

  39. Liu Y, Jourabloo A, Liu X (2018) In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 389–398

  40. Liu A, Tan Z, Li X, Wan J, Escalera S, Guo G, Li SZ (2019)Static and dynamic fusion for multi-modal cross-ethnicity face anti-spoofing. arXiv preprint arXiv:1912.02340

  41. Määttä J, Hadid A, Pietikäinen M (2011) In: 2011 international joint conference on Biometrics (IJCB), IEEE, pp 1–7

  42. Nagpal C, Dubey SR (2018) A performance evaluation of convolutional neural networks for face anti spoofing. arXiv preprint arXiv:1805.04176

  43. Niu Z, Zhou M, Wang L, Gao X, Hua G (2016) In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4920–4928

  44. Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L, et al (2019) In: Advances in Neural Information Processing Systems, pp 8024–8035

  45. Poh MZ, McDuff DJ, Picard RW (2011) Advancements in noncontact, multiparameter physiological measurements using a webcam. IEEE Trans Biomed Eng 58(1):7–11

    Article  Google Scholar 

  46. Raghavendra R, Busch C (2014) In: 2014 17th International Conference on Information Fusion (FUSION). IEEE, pp 1–7

  47. Ruder S (2017) An overview of multi-task learning in deep neural networks. arXiv preprint arXiv:1706.05098

  48. Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) In: Proceedings of the IEEE international conference on computer vision, pp 618–626

  49. Shao R, Lan X, Li J, Yuen PC (2019) In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 10,023–10,031

  50. Shao R, Lan X, Yuen PC (2017) In: 2017 IEEE International Joint Conference on Biometrics (IJCB), IEEE, pp 748–755

  51. Shao R, Perera P, Yuen PC, Patel VM (2020) Federated face anti-spoofing. arXiv preprint arXiv:2005.14638

  52. Sun W, Song Y, Huang J, Kot AC (2020) Face spoofing detection based on local ternary label supervision in fully convolutional networks. IEEE Trans Inf Forensics Secur PP(99):1–1

    Google Scholar 

  53. Tian Y, Zhang K, Wang L, Sun Z (2020) Face anti-spoofing by learning polarization cues in a real-world scenario. arXiv preprint arXiv:2003.08024

  54. Tran D, Bourdev L, Fergus R, Torresani L, Paluri M (2015) In: Proceedings of the IEEE international conference on computer vision, pp 4489–4497

  55. Tu X, Fang Y (2017) In: International Conference on Neural Information Processing, Springer, pp 686–695

  56. Tu X, Zhao J, Xie M, Du G, Zhang H, Li J, Ma Z, Feng J (2019) Learning generalizable and identity-discriminative representations for face anti-spoofing. arXiv preprint arXiv:1901.05602

  57. Wang Y, Nian F, Li T, Meng Z, Wang K (2017) Robust face anti-spoofing with depth information. J Vis Commun Image Represent 49:332–337

    Article  Google Scholar 

  58. Wang Z, Yu Z, Zhao C, Zhu X, Qin Y, Zhou Q, Zhou F, Lei Z (2020) Deep spatial gradient and temporal depth learning for face anti-spoofing

  59. Wang Z, Zhao C, Qin Y, Zhou Q, Qi G, Wan J, Lei Z (2018) Exploiting temporal and depth information for multi-frame face anti-spoofing. arXiv preprint arXiv:1811.05118

  60. Wen D, Han H, Jain AK (2015) Face spoof detection with image distortion analysis. IEEE Trans Inf Forensics Secur 10(4):746–761

    Article  Google Scholar 

  61. Wu J, Yu X, Liu B, Wang Z, Chandraker M (2020) Uncertainty-aware physically-guided proxy tasks for unseen domain face anti-spoofing. arXiv preprint arXiv:2011.14054

  62. Xu Z, Li S, Deng W (2015) In: 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR). IEEE, pp 141–145

  63. Yang J, Lei Z, Liao S, Li SZ (2013) Face liveness detection with component dependent descriptor. ICB 1:2

    Google Scholar 

  64. Yang J, Lei Z, Li SZ (2014) Learn convolutional neural network for face anti-spoofing. arXiv preprint arXiv:1408.5601

  65. Yang X, Luo W, Bao L, Gao Y, Liu W (2020) In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

  66. Yi D, Lei Z, Zhang Z, Li SZ (2014) In: Handbook of Biometric Anti-Spoofing, Springer, pp 83–102

  67. Yu Z, Li X, Niu X, Shi J, Zhao G (2020) In: European Conference on Computer Vision, Springer, pp 557–575

  68. Yu Z, Qin Y, Li X, Wang Z, Zhao C, Lei Z, Zhao G (2020) In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp 650–651

  69. Zhang KY, Yao T, Zhang J, Tai Y, Ding S, Li J, Huang F, Song H, Ma L (2020) In: European Conference on Computer Vision. Springer, pp 641–657

  70. Zhang Z, Yan J, Liu S, Lei Z, Yi D, Li SZ (2012) In: 2012 5th IAPR international conference on Biometrics (ICB), IEEE, pp 26–31

  71. Zhao J, Cheng Y, Xu Y, Xiong L, Li J, Zhao F, Jayashree K, Pranata S, Shen S, Xing J, et al (2018) In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2207–2216

  72. Zhao C, Qin Y, Wang Z, Fu T, Shi H (2019) Meta anti-spoofing: Learning to learn in face anti-spoofing. arXiv preprint arXiv:1904.12490

  73. Zhu H, Zhang Y, Li G, Zhang J, Shan H (2020) Ordinal distribution regression for gait-based age estimation. SCIENCE CHINA Inf Sci 63(2):1–14

    Google Scholar 

Download references

Acknowledgements

This work is funded by National Natural Science Foundation of China (Grant No. 61806185, 61802361), Technology Innovation and Application Development Project in Chongqing (cstc2019jscx-msxmX0299, cstc2019jscx-gksbX0073).

Author information

Authors and Affiliations

  1. School of Computer Science, University of South China, 28 Changsheng West Road, Hengyang, 421001, China

    Fangling Jiang

  2. Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, 266 Fangzheng Avenue, Chongqing, 400714, China

    Fangling Jiang, Pengcheng Liu & Xiang-Dong Zhou

  3. University of Chinese Academy of Sciences, 19 Yuquan Road, Beijing, 100049, China

    Fangling Jiang, Pengcheng Liu & Xiang-Dong Zhou

Authors
  1. Fangling Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Pengcheng Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiang-Dong Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Fangling Jiang.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

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

Jiang, F., Liu, P. & Zhou, XD. Ordinal regression with representative feature strengthening for face anti-spoofing. Neural Comput & Applic 34, 15963–15979 (2022). https://doi.org/10.1007/s00521-022-07272-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-022-07272-8

Keywords

Search

Navigation