A Novel Hybrid Approach for 3D Face Recognition Based on Higher Order Tensor

  • Mohcene BessaoudiEmail author
  • Mebarka Belahcene
  • Abdelmalik Ouamane
  • Ammar Chouchane
  • Salah Bourennane
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 50)


This paper presents a new hybrid approach for 3D face verification based on tensor representation in the presence of illuminations, expressions and occlusion variations. Depth face images are divided into sub-region and the Multi-Scale Local Binarised Statistical Image Features (MSBSIF) histogram are extracted from each sub-region and arranged as a third order tensor. Furthermore, to reduce the dimensionality of this tensor data, we use a novel hybrid approach based on two steps of dimensionality reduction multilinear and non-linear. Firstly, Multilinear Principal Component Analysis (MPCA) is used. MPCA projects the input tensor in a new lower subspace in which the dimension of each tensor mode is reduced. After that, the non-linear Exponential Discriminant Analysis (EDA) is used to discriminate the faces of different persons. Finally, the matching is performed using distance measurement. The proposed approach (MPCA+EDA) has been tested on the challenging face database Bosporus 3D and the experimental results show that our method achieves a high verification performance compared with the state of the art.


3D face verification Depth image Tensor representation Histograms local features 


  1. 1.
    Kakadiaris, I.A., Toderici, G., Evangelopoulos, G., Passalis, G., Chu, D., Zhao, X., Shah, S.K., Theoharis, T.: 3D-2D face recognition with pose and illumination normalization. Comput. Vis. Image Underst. 154, 137–151 (2017)CrossRefGoogle Scholar
  2. 2.
    Soltanpour, S., Boufama, B., Jonathan Wu, Q.M.: A survey of local feature methods for 3D face recognition. Pattern Recogn. 72, 391–406 (2017)CrossRefGoogle Scholar
  3. 3.
    Elaiwat, S., Bennamoun, M., Boussaïd, F., et al.: A curvelet-based approach for textured 3D face recognition. Pattern Recogn. 48(4), 1235–1246 (2015)CrossRefGoogle Scholar
  4. 4.
    Wang, X., Ruan, Q., Ming, Y.: 3D face recognition using corresponding point direction measure and depth local features. In: 2010 IEEE 10th International Conference on Signal Processing (ICSP), pp. 86–89. IEEE (2010)Google Scholar
  5. 5.
    Ming, Y.: Rigid-area orthogonal spectral regression for efficient 3D face recognition. Neurocomputing 129, 445–457 (2014)CrossRefGoogle Scholar
  6. 6.
    Abdi, H., Williams, L.J.: Principal component analysis. Wiley Interdisc. Rev. Comput. Stat. 2(4), 433–459 (2010)CrossRefGoogle Scholar
  7. 7.
    Pang, Y., Wang, S., Yuan, Y.: Learning regularized LDA by clustering. IEEE Trans. Neural Networks 25(12), 2191–2201 (2014)CrossRefGoogle Scholar
  8. 8.
    Welling, M.: Kernel principal components analysis. Adv. Neura L Inf. Process. Syst. 15, 70–72 (2003)Google Scholar
  9. 9.
    Zhang, T., Fang, B., Tang, Y.Y., et al.: Generalized discriminant analysis: a matrix exponential approach. IEEE Trans. Syst. Man Cybern. Part B (Cybernetics) 40(1), 186–197 (2010)Google Scholar
  10. 10.
    Lai, Z., Xu, Y., Yang, J., et al.: Sparse tensor discriminant analysis. IEEE Trans. Image Process. 22(10), 3904–3915 (2013)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Lu, H., Plataniotis, K.N., Venetsanopoulos, A.N.: MPCA: multilinear principal component analysis of tensor objects. IEEE Trans. Neural Networks 19(1), 18–39 (2008)CrossRefGoogle Scholar
  12. 12.
    Arashloo, S.R.: Multiscale binarised statistical image features for symmetric unconstrained face matching. In: 2014 22nd Iranian Conference on Electrical Engineering (ICEE), pp. 1377–1382. IEEE (2014)Google Scholar
  13. 13.
    Liu, Y., Liu, Y., Zhong, S.: Tensor distance based multilinear globality preserving embedding: a unified tensor based dimensionality reduction framework for image and video classification. Expert Syst. Appl. 39(12), 10500–10511 (2012)CrossRefGoogle Scholar
  14. 14.
    Ouamane, A., Belahcene, M., Benakcha, A., et al.: Robust multimodal 2D and 3D face authentication using local feature fusion. SIViP 10(1), 129–137 (2016)CrossRefGoogle Scholar
  15. 15.
    Kannala, J., Rahtu, E., BSIF: binarized statistical image features. In: 2012 21st International Conference on Pattern Recognition (ICPR), pp. 1363–1366. IEEE (2012)Google Scholar
  16. 16.
    Ammar, C., Mebarka, B., Abdelmalik, O., et al.: Evaluation of histograms local features and dimensionality reduction for 3D face verification. J. Inf. Process. Syst. 12(3), 468–488 (2016)Google Scholar
  17. 17.
    Ouamane, A., Chouchane, A., Boutellaa, E., et al.: Efficient tensor-based 2d + 3d face verification. IEEE Trans. Inf. Forensics Secur. 12(11), 2751–2762 (2017)CrossRefGoogle Scholar
  18. 18.
    Savran, A., Alyüz, N., Dibeklioğlu, H., et al.: Bosphorus database for 3D face analysis. In: Biometrics and Identity Management, pp. 47–56 (2008)Google Scholar
  19. 19.
    Erdogmus, N., Dugelay, J.-L.: 3D assisted face recognition: dealing with expression variations. IEEE Trans. Inf. Forensics Secur. 9(5), 826–838 (2014)CrossRefGoogle Scholar
  20. 20.
    Liu, P., Wang, Y., Huang, D., et al.: Learning the spherical harmonic features for 3-D face recognition. IEEE Trans. Image Process. 22(3), 914–925 (2013)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Mohcene Bessaoudi
    • 1
    Email author
  • Mebarka Belahcene
    • 1
  • Abdelmalik Ouamane
    • 1
  • Ammar Chouchane
    • 1
  • Salah Bourennane
    • 2
  1. 1.LI3C LaboratoryUniversity of BiskraBiskraAlgeria
  2. 2.Institut FresnelUniversité de MarseilleMarseilleFrance

Personalised recommendations