Advertisement

Automatic Synthesis Approach for Unconstrained Face Images Based on Generic 3D Shape Model

  • Hamid OuananEmail author
  • Mohammed Ouanan
  • Brahim Aksasse
Conference paper
  • 111 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1076)

Abstract

Faces captured in unconstrained conditions represent a myriad of challenges like occlusions, non-frontal poses, etc. Compared to the other variations, pose variation is one of the most difficult problems in face recognition. To this end, we propose a new automatic synthesis approach of frontal facing view of unconstrained face images which are based on the use of a generic 3D shape model and accurate localization of facial feature points. On another hand, we have used the same approach as data augmentation technique for enriching a small dataset with important facial appearance variations by manipulating the faces that it contains so as to improve the convolutional neural network (CNN) performances and avoid overfitting. This is done by using a camera model to generate multiple views covering possible poses synthesized from the 3D face model used.

Keywords

Unconstrained conditions 3D face model Pose estimation Overfitting Deep learning 

References

  1. 1.
    Ouanan, H., Ouanan, M., Aksasse, B.: Implementation and optimization of face detection framework based on openCv library on mobile platforms using Davinci’s technology. Int. J. Imaging Robot. 16(2), 118–131 (2016)Google Scholar
  2. 2.
    Ding, C., Tao, D.: A comprehensive survey on pose-invariant face recognition. ACM Trans. Intell. Syst. Technol. 7(3), 01–42 (2016)CrossRefGoogle Scholar
  3. 3.
    Ouanan, H., Ouanan, M., Aksasse, B.: Novel approach to pose invariant face recognition. Proc. Comput. Sci. (2017)Google Scholar
  4. 4.
    Ouanan, H., Ouanan, M., Aksasse, B.: Myface: unconstrained face recognition. Lecture Notes in Networks and Systems (2017)Google Scholar
  5. 5.
    Jiang, L., Zhang, J., Deng, B., Li, H., Liu, L.: 3D face reconstruction with geometry details from a single image. arXiv:1702.05619 (2017)
  6. 6.
    Penate-Sanchez, A., Andrade-Cetto, J., Moreno-Noguer, F.: Exhaustive linearization for robust camera pose and focal length estimation. IEEE Trans. Pattern Anal. Mach. Intell. 35(10), 2387–2400 (2013)CrossRefGoogle Scholar
  7. 7.
    Abdel-Aziz, Y.I., Karara, H.M., Hauck, M.: Direct linear transformation from comparator coordinates into object space coordinates in close-range photogrammetry. Photogramm. Eng. Remote Sens. 81(2), 103–107 (2015)CrossRefGoogle Scholar
  8. 8.
    Zuliani, M.: Ransac toolbox for matlab. Available at http://www.mathworks.com/matlabcentral/fileexchange/18555 (2008)
  9. 9.
    Zhu, X., Ramanan, D.: Face detection, pose estimation, and landmark localization in the wild. In: IEEE Computer Vision and Pattern Recognition (CVPR), pp. 2879–2886 (2012)Google Scholar
  10. 10.
    Ouanan, H., Ouanan, M., Aksasse, B.: Face recognition using deep features. In: International Conference on Advanced Information Technology, Services and Systems. Springer, Cham, pp. 78–85 (2017)Google Scholar
  11. 11.
    Ouanan, H., Ouanan, M., Aksasse, B.: Non-linear dictionary representation of deep features for face recognition from a single sample per person. Proc. Comput. Sci. 127, 114–122 (2018)CrossRefGoogle Scholar
  12. 12.
    Taigman, Y., Yang, M., Ranzato, M.A., Wolf, L.: DeepFace: closing the gap to human-level performance in face verification. In: Proceedings of IEEE Conference on IEEE Computer Vision and Pattern Recognition, pp. 1701–1708 (2014)Google Scholar
  13. 13.
    Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)Google Scholar
  14. 14.
    Huang, G.B., Ramesh, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments, vol. 1, no. 2, pp. 07-49. University of Massachusetts, Amherst, Technical Report (2007)Google Scholar
  15. 15.
    Sun, Y., Wang, X., Tang, X.: Deep learning face representation from predicting 10,000 classes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2014)Google Scholar
  16. 16.
    Chen, D., Cao, X., Wang, L., Wen, F., Sun, J.: Bayesian face revisited: a joint formulation. In: Proceedings of the European Conference on Computer Vision, pp. 566–579 (2012)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.National School of Applied SciencesSultan Moulay Slimane UniversityBeni MellalMorocco
  2. 2.Dept. of Computer Science, M2I Laboratory, Faculty of Science and TechniquesMoulay Ismail UniversityErrachidiaMorocco

Personalised recommendations