On the Use of Pre-trained Neural Networks for Different Face Recognition Tasks

  • Leyanis López-Avila
  • Yenisel Plasencia-Calaña
  • Yoanna Martínez-Díaz
  • Heydi Méndez-Vázquez
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10657)


Deep Convolutional Neural Networks (DCNN) are the state-of-the-art in face recognition. In this paper, we study different representations obtained from a pre-trained DCNN, in order to determine the best way in which they can be used in different tasks. In particular, we evaluate the use of intermediate representations independently or combined with a Fisher Vector approach, or with a Bilinear model. From our study, we found that convolutional features may be more suitable than the features obtained from the last fully connected layers for different applications.


Convolutional neural networks Deep learning Face recognition Transfer learning 


  1. 1.
    Belhumeur, P.N., Hespanha, J.P., Kriegman, D.J.: Eigenfaces vs. fisherfaces: recognition using class specific linear projection. IEEE Trans. Pattern Anal. Mach. Intell. 19(7), 711–720 (1997)CrossRefGoogle Scholar
  2. 2.
    Chen, J.C., Zheng, J., Patel, V.M., Chellappa, R.: Fisher vector encoded deep convolutional features for unconstrained face verification. In: ICIP, pp. 2981–2985. IEEE (2016)Google Scholar
  3. 3.
    Chowdhury, A.R., Lin, T.Y., Maji, S., Learned-Miller, E.G.: One-to-many face recognition with bilinear CNNs. In: WACV, pp. 1–9. IEEE Computer Society (2016)Google Scholar
  4. 4.
    Han, H., Klare, B., Bonnen, K., Jain, A.K.: Matching composite sketches to face photos: a component-based approach. IEEE Trans. Inf. Forensics and Secur. 8(1), 191–204 (2013)CrossRefGoogle Scholar
  5. 5.
    Huang, G.B., Ramesh, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments. Technical report, Technical Report 07–49, University of Massachusetts, Amherst (2007)Google Scholar
  6. 6.
    Jin, Y., Lu, J., Ruan, Q.: Coupled discriminative feature learning for heterogeneous face recognition. IEEE Trans. Inf. Forensics Secur. 10(3), 640–652 (2015)CrossRefGoogle Scholar
  7. 7.
    Lin, T.Y., RoyChowdhury, A., Maji, S.: Bilinear CNN models for fine-grained visual recognition. CoRR abs/1504.07889 (2015)Google Scholar
  8. 8.
    Mehdipour Ghazi, M., Kemal Ekenel, H.: A comprehensive analysis of deep learning based representation for face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 34–41 (2016)Google Scholar
  9. 9.
    Mittal, P., Vatsa, M., Singh, R.: Composite sketch recognition via deep network - a transfer learning approach. In: International Conference on Biometrics, ICB 2015, Phuket, Thailand, 19–22 May 2015, pp. 251–256 (2015)Google Scholar
  10. 10.
    Ouyang, S., Hospedales, T., Song, Y.Z., Li, X., Loy, C.C., Wang, X.: A survey on heterogeneous face recognition. Image Vis. Comput. 56(C), 28–48 (2016)CrossRefGoogle Scholar
  11. 11.
    Parkhi, O.M., Vedaldi, A., Zisserman, A.: Deep face recognition. In: BMVC, vol. 1, p. 6 (2015)Google Scholar
  12. 12.
    Simonyan, K., Parkhi, O.M., Vedaldi, A., Zisserman, A.: Fisher vector faces in the wild. In: BMVC, vol. 2, p. 4 (2013)Google Scholar
  13. 13.
    Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: Deepface: closing the gap to human-level performance in face verification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1701–1708 (2014)Google Scholar
  14. 14.
    Zhao, W., Chellappa, R., Phillips, P.J., Rosenfeld, A.: Face recognition: a literature survey. ACM Comput. Surv. 35(4), 399–458 (2003)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Leyanis López-Avila
    • 1
  • Yenisel Plasencia-Calaña
    • 1
  • Yoanna Martínez-Díaz
    • 1
  • Heydi Méndez-Vázquez
    • 1
  1. 1.Advanced Technologies Application CenterHavanaCuba

Personalised recommendations