Foveated Vision for Deepface Recognition

  • Souad Khellat-Kihel
  • Andrea Lagorio
  • Massimo TistarelliEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11896)


In the last decade deep learning techniques have strongly influenced many aspects of computational vision. Many difficult vision tasks can now be performed by deploying a properly tailored and trained deep network. The enthusiasm for deep learning is unfortunately paired by the present lack of a clear understanding of how they work and why they provide such brilliant performance. The same applies to biometric systems. Deep learning has been successfully applied to several biometric recognition tasks, including face recognition. VGG-face is possibly the first deep convolutional network designed to perform face recognition, obtaining unsurpassed performance at the time it was firstly proposed. Over the last years, several and more complex deep convolutional networks, trained on very large, mainly private, datasets, have been proposed still elevating the performance bar also on quite challenging public databases, such as the Janus IJB-A and IJB-B. Despite of the progress in the development of such networks, and the advance in the learning algorithms, the insight on these networks is still very limited. For this reason, in this paper we analyse a biologically-inspired network based on the HMAX model, not with the aim of pushing the recognition performance further, but to better understand the representation space produced by including the retino-cortical mapping performed by the log-polar image resampling.


Face representation space Hierarchical model ‘HMAX’ Biological foveated vision 



This research work has been partially supported by a grant from the European Commission (H2020 MSCA RISE 690907 “IDENTITY”), by a grant of the Italian Ministry of Research (PRIN 2015) and by a special research grant from the University of Sassari.


  1. 1.
    Maximilian, R., Tomaso, P.: Hierarchical models of object recognition in cortex. Nat. Neurosci. 2(11), 321–354 (1999)Google Scholar
  2. 2.
    Daniilidis, K.: Attentive visual motion processing: computations in the log-polar plan. In: Kropatsch, W., Klette, R., Solina, F., Albrecht, R. (eds.) Theoretical Foundations of Computer Vision. Computing Supplement, vol. 11, pp. 1–20. Springer, Vienna (1996). Scholar
  3. 3.
    Taigman, Y., Yang, M., Ranzato, M.A., Wolf, L.: DeepFace: closing the gap to human-level performance in face verification. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1701–1708 (2014)Google Scholar
  4. 4.
    Schrott, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 815–823 (2015)Google Scholar
  5. 5.
    Jun-Cheng, C., Patel, V., Chellappa, R.: Unconstrained Face Verification using Deep CNN Features. In: IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1–9 (2016)Google Scholar
  6. 6.
    Parde, C.J., et al.: Face representations in deep convolutional neural networks. In: IEEE Conference on Automatic Face and Gesture Recognition (FG), Gender and Discourse (2017)Google Scholar
  7. 7.
    O’Toole, A., Castillo, C., Parde, C.J., Hill, M.Q., Chellappa, R.: Face representation in deep convolutional neural networks. Trends Cogn. Sci. 22(9), 794–809 (2018)CrossRefGoogle Scholar
  8. 8.
    Liao, Q., Leibo, J., Poggio, T.: Learning invariant representations and applications to face verification. In: Advances in Neural Information Processing Systems 26, NIPS 2013, pp. 3057–3065 (2013)Google Scholar
  9. 9.
    Esmaili, S., Maghooli, K., Nasrabadi, A.: C3 effective features inspired from ventral and dorsal stream of visual cortex for view independent face recognition. Int. J. Adv. Comput. Sci. 5, 1–9 (2016)Google Scholar
  10. 10.
    Hu, X., Zhang, J., Li, J., Zhang, B.: Sparsity-regularized HMAX for visual recognition. PLoS One, 1–12 (2014)Google Scholar
  11. 11.
    Burt, P.G.: Smart sensing in machine vision. In: Machine Vision: Algorithms, Architectures, and Systems, pp. 1–30. Academic Press (1988)Google Scholar
  12. 12.
    Massone, L., Sandini, G., Tagliasco, V.: Form-invariant topological mapping strategy for 2-D shape recognition. In: CVGIP, vol. 30, no. 2, pp. 169–188 (1985)Google Scholar
  13. 13.
    Sandini, G., Tistarelli, M.: Vision and space-variant sensing. In: Wechsler, H. (ed.) Neural Networks for Perception: Human and Machine Perception. Academic Press (1991)Google Scholar
  14. 14.
    Schwartz, E.: Anatomical and physiological correlates of visual computation from striate to infero-temporal cortex. IEEE Trans. Syst. Man Cybern. SMC-14(2), 257–271 (1984)CrossRefGoogle Scholar
  15. 15.
    Grosso, E., Lagorio, A., Pulina, L., Tistarelli, M.: Towards practical space-variant based face recognition and authentication. In: 2nd International Workshop on Biometrics and Forensics, pp. 1–6, October 2014Google Scholar
  16. 16.
  17. 17.
  18. 18.
    Khellat-Kihel, S., Lagorio, A., Tistarelli, M.: Face recognition ‘on the move’ combining incomplete information. In: Proceedings of 6th International Workshop on Biometrics and Forensics (IWBF), pp. 1–6, September 2018Google Scholar
  19. 19.
    van der Maaten, L.J.P.: Accelerating t-SNE using tree-based algorithms. J. Mach. Learn. Res. 15, 3221–3245 (2014)MathSciNetzbMATHGoogle Scholar
  20. 20.
    CS231n: Convolutional Neural Networks for Visual Recognition, Spring 2018Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Souad Khellat-Kihel
    • 1
  • Andrea Lagorio
    • 1
  • Massimo Tistarelli
    • 1
    Email author
  1. 1.Computer Vision LaboratoryUniversity of SassariSassariItaly

Personalised recommendations