Multi-manifold Approach to Multi-view Face Recognition

  • Shireen Mohd Zaki
  • Hujun YinEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9375)


In this paper a multi-manifold approach is proposed for dealing with facial variations and limited sample availability in face recognition. Face recognition has long been an active topic in computer vision. There have been many methods proposed and most only consider frontal images with controlled lighting. However, variations in environment, pose, expression, constitute huge problems and often make practical implementation unreliable. Although these variations have been dealt with separately with varying degrees of success, a coherent approach is lacking. Here practical face recognition is regarded as a multi-view learning problem where different variations are treated as different views, which in turn are modeled by a multi-manifold. The manifold can be trained to capture and integrate various variations and hence to render a novel variation that can match the probe image. The experimental results show significant improvement over standard approach and many existing methods.


Multi-manifolds Face recognition Multi-view learning Invariant features 


  1. 1.
    Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: DeepFace: closing the gap to human-level performance in face verification. In: Conference on Computer Vision Pattern Recognition, p. 8 (2014)Google Scholar
  2. 2.
    Lu, C., Tang, X.: Surpassing human-level face verification performance on LFW with GaussianFace. In: Proceedings of the 29th AAAI Conference on Artificial Intelligence (AAAI), pp. 3811–3819 (2014)Google Scholar
  3. 3.
    Turk, M., Pentland, A.: Eigenfaces for recognition. J. Cogn. Neurosci. 3(1), 71–86 (1991)CrossRefGoogle Scholar
  4. 4.
    Hespanha, P., Kriegman, D.J., Belhumeur, P.N.: Eigenfaces vs. fisherfaces : recognition using class specific linear projection. IEEE Trans. Pattern Anal. Mach. Intell. 19(7), 711–720 (1997)CrossRefGoogle Scholar
  5. 5.
    Yang, J., Zhang, D., Frangi, A.F., Yang, J.: Two-dimensional PCA: a new approach to appearance-based face representation and recognition. IEEE Trans. Pattern Anal. Mach. Intell. 26(1), 131–137 (2004)CrossRefGoogle Scholar
  6. 6.
    Tenenbaum, J.B., de Silva, V., Langford, J.C.: A global geometric framework for nonlinear dimensionality reduction. Science 290, 2319–2323 (2000)CrossRefGoogle Scholar
  7. 7.
    Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290, 2323–2326 (2000)CrossRefGoogle Scholar
  8. 8.
    Yin, H.: Advances in adaptive nonlinear manifolds and dimensionality reduction. Front. Electr. Electron. Eng. China 6(1), 72–85 (2011)CrossRefGoogle Scholar
  9. 9.
    Kohonen, T.: The self-organizing map. Proc. IEEE 78(9), 1464–1480 (1990)CrossRefGoogle Scholar
  10. 10.
    Yin, H., Huang, W.: Adaptive nonlinear manifolds and their applications to pattern recognition. Inf. Sci. (Ny) 180(14), 2649–2662 (2010)MathSciNetCrossRefzbMATHGoogle Scholar
  11. 11.
    Yin, H.: ViSOM—a novel method for multivariate data projection and structure visualization. IEEE Trans. Neural Networks 13(1), 237–243 (2002)CrossRefGoogle Scholar
  12. 12.
    Liu, X., Lu, H., Li, W.: Multi-manifold modeling for head pose estimation. In: 2010 IEEE International Conference on Image Processing, pp. 3277–3280 (2010)Google Scholar
  13. 13.
    Wang, Y., Jiang, Y., Wu, Y., Zhou, Z.-H.: Multi-manifold clustering. In: Zhang, B.-T., Orgun, M.A. (eds.) PRICAI 2010. LNCS, vol. 6230, pp. 280–291. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  14. 14.
    Wang, Y., Jiang, Y., Wu, Y., Zhou, Z.-H.: Spectral clustering on multiple manifolds. IEEE Trans. Neural Networks 22(7), 1149–1161 (2011)CrossRefGoogle Scholar
  15. 15.
    Lu, J., Tan, Y., Wang, G.: Discriminative multi-manifold analysis for face recognition from a single training sample per person. In: 2011 International Conference on Computer Vision (ICCV), pp. 1943–1950 (2011)Google Scholar
  16. 16.
    Sun, S.: A survey of multi-view machine learning. Neural Comput. Appl. 23(7–8), 2031–2038 (2013)CrossRefGoogle Scholar
  17. 17.
    Memisevic, R.: On multi-view feature learning. In: Proceedings of the 29th International Conference on Machine Learning (ICML 2012) (2012)Google Scholar
  18. 18.
    Xu, C., Tao, D., Xu, C.: Large-margin multi-view information bottleneck. IEEE Trans. Pattern Anal. Mach. Intell. 36(8), 1559–1572 (2014)CrossRefGoogle Scholar
  19. 19.
    Cootes, T.F., Taylor, C.J., Cooper, D.H., Graham, J.: Active shape models-their training and application. Comput. Vis. Image Underst. 61(1), 38–59 (1995)CrossRefGoogle Scholar
  20. 20.
    Teijeiro-Mosquera, L., Alba-Castro, J.-L., Gonzalez-Jimenez, D.: Face recognition across pose with automatic estimation of pose parameters through AAM-based landmarking. In: 2010 20th International Conference on Pattern Recognition, no. 2, pp. 1339–1342, August 2010Google Scholar
  21. 21.
    Wiskott, L., Kr, N., Von Der Malsburg, C.: Face recognition by elastic bunch graph matching. IEEE Trans. Pattern Anal. Mach. Intell. 19(7), 1–23 (1999)Google Scholar
  22. 22.
    Sim, T., Baker, S., Bsat, M.: The CMU pose, illumination, and expression (PIE) database 2 capture apparatus and procedure, no. 1, pp. 1–6 (2002)Google Scholar
  23. 23.
    He, X., Cai, D., Niyogi, P.: Laplacian score for feature selection. In: Advances Neural Information Processing, pp. 507–514 (2005)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.School of Electrical and Electronic EngineeringThe University of ManchesterManchesterUK

Personalised recommendations