Skip to main content
SpringerLink
Log in

Deep Residual Equivariant Mapping for Multi-angle Face Recognition

  • Conference paper
  • First Online:
Biometric Recognition (CCBR 2019)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 11818))

Included in the following conference series:

Abstract

Face recognition has caught a lot of attention and plenty of valuable methods have been proposed during the past decades. However, because it is hard to learn geometrically invariant representations, existing face recognition methods still perform relatively poorly in conducting multi-angle face recognition. In this paper, we hypothesize that there is an inherent mapping between the frontal and non-frontal faces, and the non-frontal face representations can be converted into the frontal face representations by an equivariant mapping. To carry out the mapping, we propose a Multi-Angle Deep Residual Equivariant Mapping (MADREM) block which adaptively maps the non-frontal face representation to the frontal face representation. It can be considered the MADREM block carry out face alignment and face normalization in the feature space. The residual equivariant mapping block can enhance the discriminative power of the face representations. Finally, we achieve an accuracy of 99.78% on the LFW dataset and 94.25% on CFP-FP dataset based on proposed multiscale-convolution and residual equivariant mapping block.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 59.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 79.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Girshick, R.: Fast R-CNN. Computer science. arXiv preprint arXiv:1504.08083 (2015)

  2. Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2

    Chapter  Google Scholar 

  3. He, K., Zhang, X., Ren, S.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. arXiv preprint arXiv:1502.01852 (2015)

  4. Tian, C., Xu, Y., Fei, L.: Deep learning for image denoising: a survey. arXiv preprint arXiv:1810.05052v1 (2018)

  5. Xu, Y., Zhang, D., Yang, J.: A two-phase test sample sparse representation method for use with face recognition. IEEE Trans. Circuits Syst. Video Technol. 21(9), 1255–1262 (2011)

    Article  MathSciNet  Google Scholar 

  6. Xu, Y., Zhu, X., Li, Z.: Using the original and ‘symmetrical face’ training samples to perform representation based two-step face recognition. Pattern Recognit. 46(4), 1151–1158 (2013)

    Article  Google Scholar 

  7. Guo, K., Wu, S., Xu, Y.: Face recognition using both visible light image and near-infrared image and a deep network. CAAI Trans. Intell. Technol. 2(1), 39–47 (2017)

    Article  Google Scholar 

  8. Taigman, Y., Yang, M., Ranzato, M.: DeepFace: closing the gap to human-level performance in face verification. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, pp. 1701–1708. IEEE (2014)

    Google Scholar 

  9. Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. arXiv preprint arXiv:1503.03832 (2015)

  10. Sun, Y., Wang, X., Tang, X.: Deeply learned face representations are sparse, selective, and robust. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, pp. 2892–2900. IEEE (2015)

    Google Scholar 

  11. Wu, X., He, R., Sun, Z.: A light CNN for deep face representation with noisy labels. IEEE Trans. Inf. Forensics Secur. (2015)

    Google Scholar 

  12. Liu, W.: SphereFace: deep hypersphere embedding for face recognition. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, pp. 6738–6746 (2017)

    Google Scholar 

  13. Wang, H., Wang, Y., Zhou, Z.: CosFace: large margin cosine loss for deep face recognition. arXiv preprint arXiv:1801.09414 (2018)

  14. Deng, J., Guo, J., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face Recognition.arXiv preprint arXiv:1801.07698 (2018)

  15. Yim, J., Jung, H., Yoo, B.I.: Rotating your face using multi-task deep neural network. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, pp. 676–684. IEEE (2015)

    Google Scholar 

  16. Jourabloo, A., Liu, X.: Large-pose face alignment via CNN-based dense 3D model fitting. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, pp. 4188–4196. IEEE (2016)

    Google Scholar 

  17. Tran, L., Yin, X., Liu, X.: Disentangled representation learning GAN for pose-invariant face recognition. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1283–1292. Springer, Honolulu (2017)

    Google Scholar 

  18. Masi, I., Rawls, S., Medioni, G.: Pose-aware face recognition in the wild. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, pp. 4838–4846. IEEE (2016)

    Google Scholar 

  19. Liao, S., Jain, A.K., Li, S.Z.: Partial face recognition: alignment-free approach. IEEE Trans. Pattern Anal. Mach. Intell. 35, 1193–1205 (2013)

    Article  Google Scholar 

  20. Cao, K., Rong, Y., Li, C.: Pose-robust face recognition via deep residual equivariant Mapping. arXiv preprint arXiv:1803.00839 (2018)

  21. Lenc, K., Vedaldi, A.: Understanding image representations by measuring their equivariance and equivalence. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, pp. 991–999 (2015)

    Google Scholar 

  22. Zhang, X., Sugano, Y., Fritz, M.: Appearance-based gaze estimation in the wild. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, pp. 4511–4520 (2015)

    Google Scholar 

  23. Ruiz, N., Chong, E., Rehg, J.M.: Fine-grained head pose estimation without keypoints. arXiv preprint arXiv:1710.00925 (2017)

  24. Huang, G.B., Mattar, M., Berg, T.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments. In: Workshop on Faces in ‘Real-Life’ Images: Detection, Alignment, and Recognition, Marseille (2008)

    Google Scholar 

  25. Sengupta, S., Chen, J., Castillo, C.: Frontal to profile face verification in the wild. In: 2016 IEEE Winter Conference on Applications of Computer Vision, Lake Placid, pp. 1–9 (2016)

    Google Scholar 

  26. Guo, Y., Zhang, L., Hu, Y., He, X., Gao, J.: MS-Celeb-1M: a dataset and benchmark for large-scale face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 87–102. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46487-9_6

    Chapter  Google Scholar 

  27. Zhang, K., Zhang, Z., Li, Z.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process. Lett. 23(10), 1499–1503 (2016)

    Article  Google Scholar 

  28. Nguyen, H.V., Bai, L.: Cosine similarity metric learning for face verification. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010. LNCS, vol. 6493, pp. 709–720. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-19309-5_55

    Chapter  Google Scholar 

  29. Parkhi, O.M., Vedaldi, A., Zisserman, A.: Deep face recognition. bmvc 1(3), 6 (2015)

    Google Scholar 

  30. Liu, J., Deng, Y., Bai, T.: Targeting ultimate accuracy: face recognition via deep embedding. arXiv preprint arXiv:1506.07310 (2015)

  31. Chen, J., Patel,V. M., Chellappa, R.: Unconstrained face verification using deep CNN features. arXiv preprint arXiv:1508.01722 (2015)

  32. Sankaranarayanan, S., Alavi, A., Castillo, C.: Triplet probabilistic embedding for face verification and clustering. arXiv preprint arXiv:1604.05417 (2016)

  33. Sun, Y., Wang, X., Tang, X.: Deep learning face representation by joint identification-verification. arXiv preprint arXiv:1406.4773 (2014)

  34. Wen, Y., Zhang, K., Li, Z., Qiao, Yu.: A discriminative feature learning approach for deep face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 499–515. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46478-7_31

    Chapter  Google Scholar 

  35. Szegedy, C., Ioffe, S., Vanhoucke, V.: Inception-v4, Inception-ResNet and the impact of residual connections on learning. arXiv preprint arXiv:1602.07261 (2016)

  36. Gao, S.-H., Cheng, M.-M., Zhao, K., et al.: Res2Net: a new multi-scale backbone architecture. arXiv preprint arXiv:1904.01169 (2019)

  37. Chen, J.C., Zheng, J., Patel, V.M., et al.: Fisher vector encoded deep convolutional features for unconstrained face verification. In: IEEE International Conference on Image Processing (2016)

    Google Scholar 

  38. Peng, X., Yu, X., Sohn, K., et al.: Reconstruction-based disentanglement for pose-invariant face recognition. arXiv preprint arXiv:1702.03041 (2017)

  39. Deng, J., Cheng, S., Xue, N., et al: UV-GAN: adversarial facial UV map completion for pose-invariant face recognition. arXiv preprint arXiv:1712.04695 (2017)

Download references

Acknowledgement

This work was funded by Economic, Trade and information Commission of Shenzhen Municipality (20170504160426188) and National Natural Science Foundation of China (U1836205).

Author information

Authors and Affiliations

  1. Bio-Computing Research Center, Harbin Institute of Technology, Shenzhen, China

    Wei Liu, Lintai Wu & Yong Xu

  2. IFLYTEK Co., Ltd., Hefei, China

    Dan Wang

Authors
  1. Wei Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lintai Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yong Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Dan Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yong Xu .

Editor information

Editors and Affiliations

  1. Chinese Academy of Sciences, Beijing, China

    Zhenan Sun

  2. Chinese Academy of Sciences, Beijing, China

    Ran He

  3. Tsinghua University, Beijing, China

    Jianjiang Feng

  4. Chinese Academy of Sciences, Beijing, China

    Shiguang Shan

  5. Tsinghua University, Shenzhen, China

    Zhenhua Guo

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Liu, W., Wu, L., Xu, Y., Wang, D. (2019). Deep Residual Equivariant Mapping for Multi-angle Face Recognition. In: Sun, Z., He, R., Feng, J., Shan, S., Guo, Z. (eds) Biometric Recognition. CCBR 2019. Lecture Notes in Computer Science(), vol 11818. Springer, Cham. https://doi.org/10.1007/978-3-030-31456-9_16

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-31456-9_16

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-31455-2

  • Online ISBN: 978-3-030-31456-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation