Skip to main content
SpringerLink
Log in

Convolutional Siamese neural network for few-shot multi-view face identification

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

The face is the most popular biometric trait for human recognition. The goal of a face identification system is to mimic the human recognition process and automate applications such as border control, passport control, criminal investigation, and terrorist identification. In this study, we examine multi-view face identification systems, particularly when there are limited samples of images per angle of view per identity. We propose a multi-view face identification system based on the Siamese Neural Network (SNN), and we evaluate its performance under two training scenarios: using only same-angle images and using both same-angle and different-angle images. Our system is also trained with only one image per angle for the training set. The results of our experiments on Umist and Schneiderman databases demonstrate that the proposed SNN model is the optimal solution for few-shot multi-view face identification, with an accuracy of 74.4% compared to 37% for the VGGFace model and 77% compared to 76% for a CNN model trained from scratch, when using one image per angle for the training set on the Schneiderman database with an angle of view + 10. The accuracy was 59% for the VGGFace model. The proposed model can be downloaded from this link: https://github.com/Majdouline-Meddad/SNN-for-Multi-view-face-identification.

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

Similar content being viewed by others

Data availability

The used datasets are available in references [27, 28]. The proposed model can be downloaded from this link: https://github.com/Majdouline-Meddad/SNN-for-Multi-view-face-identification[29, 30].

References

  1. Zhu, Z., Luo, P., Wang, X., Tang, X.: Multi-view perceptron: a deep model for learning face identity and view representations. NIPS (2014)

  2. Putra, A.A.R., Setumin, S.: The performance of Siamese neural network for face recognition using different activation functions. In: International Conference of Technology, Science and Administration (ICTSA), vol. 2021, pp. 1–5 (2021) https://doi.org/10.1109/ICTSA52017.2021.94065

  3. Bertinetto, L., Valmadre, J., João, F., Henriques, A.V., Torr, P.H.S.: Fully-convolutional siamese networks for object tracking. In: Computer Vision ECCV 2016 Workshops Springer International Publishing (2016)

  4. Rajdeep, C., Soham, R., Satyabrata, R.: A Siamese neural network-based face recognition from masked faces. In: International Conference on Advanced Network Technologies and Intelligent Computing (2022)

  5. Debaditya, S., Kar, T.: FedAffect: few-shot federated learning for facial expression recognition. 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) (2021)

  6. Hayale, W., Negi, P.S., Mahoor, M.: Deep Siamese neural networks for facial expression recognition in the wild. IEEE Trans. Affect. Comput. (2021). https://doi.org/10.1109/TAFFC.2021.3077248

    Article  Google Scholar 

  7. Gabriel, S., Alceu, Jr., Rafael, V., William, S., David, M.: Open-set face recognition for small galleries using siamese networks (2021) https://doi.org/10.1109/IWSSIP48289.2020.9145245. arXiv:2105.06967v1 [cs.CV]

  8. Jalal, A.S., Bhatnagar, C., Khan, M.A., Solanki, M. S.: LBP based face recognition system for multi-view face using single sample per person. 2016 11th International Conference on Industrial and Information Systems (ICIIS), Roorkee, pp. 414–419 (2016). https://doi.org/10.1109/ICIINFS.2016.8262976

  9. Kurita, T.,Hosoi, T., Hidaka, A.: Principal component analysis of multi-view images for viewpoint-independent face recognition. In: IEEE International Conference on Video and Signal Based Surveillance, Sydney, pp. 55–55 (2006). https://doi.org/10.1109/AVSS.2006.93

  10. Ahmed, F.: A comparative study of human faces recognition using principle components aanalysis ans linear discriminant analysis techniques. J. Eng. Sustain, Dev (2017)

    Google Scholar 

  11. Zhou, H., Chen, P., Shen, W.: A multi view face recognition system based on cascade face detector and improved dlib. In: International Symposium on Multispectral Image Processing and Pattern Recognition (2017)

  12. Li, Y., Gong, S., Liddell, H.: Support vector regression and classification based multi-view face detection and recognition. In: Proceedings 4th IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580), pp. 300–305 (2000) https://doi.org/10.1109/AFGR.2000.840650

  13. Chouaib, M., Sanaa, G., Mounia, M., Abdul, W., Mohammed, R.: Inter-communication classification for multi-view face recognition. Int. Arab J. Inf, Technol (2014)

    Google Scholar 

  14. Gu, S., Ying, T., He, X.: Laplacian smoothing transform for face recognition. Sci. China Inf, Sci (2010)

    Book  MATH  Google Scholar 

  15. Gu, S., Tan, Y., He, X.: Discriminant analysis via support vectors. Neurocomputing (2010)

  16. Jania, A., Simon, P.: Face pose estimation in uncontrolled environments. In: British Machine Vision Conference (2009)

  17. Tuncer, T., Dogan, S., Abdar, M., Basiri, M.E., Pławiak, P.: Face recognition with triangular fuzzy set-based local cross patterns in wavelet domain. Symmetry 11(6), 787 (2019). https://doi.org/10.3390/sym11060787

    Article  Google Scholar 

  18. Cao, K., Rong, Y., Li, C., Tang, X., Loy, C.C.: Pose-robust face recognition via deep residual equivariant mapping. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, vol. 2018, pp. 5187–5196 (2018). https://doi.org/10.1109/CVPR.2018.00544

  19. Gao, W., Zhao, X., Zou, J.: Boosting face recognition under drastic views using a pose autoaugment manner. Appl, Sci (2020)

    Google Scholar 

  20. Xiongjun, Z., Qingxiang, W., Han, M., Huang, X.: Multi-view face recognition and verification based on convolutional neural network. In: International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (2018)

  21. Majdouline, M., Chouaib, M., Mounia, M., Mohammed, R.: A hybrid face identification system using a compressed CNN in a big data environment for embedded devices. Int. J. Comput. Dig. Syst. 9(4) (2020)

  22. Bromley, J., Guyon, I., LeCun, Y., Sickinger, E., Shah, R.: Signature verification using a Siamese time delay neural network. In: Advances in Neural Information Processing Systems (1994)

  23. Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively with application to face verification. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05) (2005)

  24. Sarhan, S., Nasr, A.A., Shams, M.Y.: Multipose face recognition-based combined adaptive deep learning vector quantization. In: Computational Intelligence and Neuroscience2020, ISSN: 1687-5265 (2020) https://doi.org/10.1155/2020/8821868. https://www.hindawi.com/journals/cin/2020/8821868/

  25. Kisku, D.R., Mehrotra, H., Gupta, P., Sing, J.K.: Robust multi-camera view face recognition. Computing Research Repository (2010)

  26. Vareto, R., Silva, S., Costa, F., Schwartz, W.R.: Towards openset face recognition using hashing functions. In: 2017 IEEE International Joint Conference on Biometrics (IJCB) (2017)

  27. Graham, D.B., Allinson, N.M.: Virtual eigen signatures for general purpose face recognition: from theory to applications. Comput. Syst, Sci (1998)

    Google Scholar 

  28. http://robotics.csie.ncku.edu.tw/Databases/FaceDetect_PoseEstimate.htm#Our_Database_

  29. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. ICLR 2015 (2015)

  30. Sun, Y., Liang, D., Wang, X., Tang, X.: DeepID3: face recognition with very deep neural networks (2015) arXiv preprint arXiv:1502.00873

Download references

Acknowledgements

Majdouline Meddad acknowledges the financial support of the “Centre National pour la Recherche Scientifique et Technique” CNRST, Morocco.

Funding

Financial support from the ”Centre National pour la Recherche Scientifique et Technique (CNRST)”, Morocco.

Author information

Authors and Affiliations

  1. LRIT Laboratory, Associated Unit to CNRST (URAC 29), Rabat IT Center, Faculty of Sciences, Mohammed V University in Rabat, Rabat, Morocco

    Majdouline Meddad, Mounia Mikram & Mohammed Rziza

  2. Scientific Institute of Rabat, Mohammed V University in Rabat, Rabat, Morocco

    Chouaib Moujahdi

  3. Meridian Team, LYRICA Laboratory, School of Information Sciences, Rabat, Morocco

    Mounia Mikram

Authors
  1. Majdouline Meddad
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chouaib Moujahdi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mounia Mikram
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Mohammed Rziza
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors have participate equally in the elaboration of this work. They have all read and agreed to the published version of the manuscript. All authors did and reviewed the manuscript.

Corresponding author

Correspondence to Majdouline Meddad.

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

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

Meddad, M., Moujahdi, C., Mikram, M. et al. Convolutional Siamese neural network for few-shot multi-view face identification. SIViP 17, 3135–3144 (2023). https://doi.org/10.1007/s11760-023-02535-w

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11760-023-02535-w

Keywords

Search

Navigation