Robust Head Pose Estimation Using Supervised Manifold Learning

  • Chiraz BenAbdelkader
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6316)


We address the problem of fine-grain head pose angle estimation from a single 2D face image as a continuous regression problem. Currently the state of the art, and a promising line of research, on head pose estimation seems to be that of nonlinear manifold embedding techniques, which learn an ”optimal” low-dimensional manifold that models the nonlinear and continuous variation of face appearance with pose angle. Furthermore, supervised manifold learning techniques attempt to achieve this robustly in the presence of latent variables in the training set (especially identity, illumination, and facial expression), by incorporating head pose angle information accompanying the training samples. Most of these techniques are designed with the classification scenario in mind, however, and are not directly applicable to the regression scenario where continuous numeric values (pose angles), rather than class labels (discrete poses), are available. In this paper, we propose to deal with the regression case in a principled way. We present a taxonomy of methods for incorporating continuous pose angle information into one or more stages of the manifold learning process, and discuss its implementation for Neighborhood Preserving Embedding (NPE) and Locality Preserving Projection (LPP). Experiments are carried out on a face dataset containing significant identity and illumination variations, and the results show that our regression-based approach far outperforms previous supervised manifold learning methods for head pose estimation.


Face Recognition Face Image Support Vector Regression Illumination Variation Locality Preserve Projection 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Tian, Y., Brown, L., Connell, J.: Absolute head pose estimation from overhead wide-angle cameras. In: IEEE Workshop on Analysis and Modeling of Faces and Gestures (2003)Google Scholar
  2. 2.
    Wu, J., Trivedi, M.M.: A two-stage pose estimation framework and evaluation. Pattern Recognition 41, 1138–1158 (2008)zbMATHCrossRefGoogle Scholar
  3. 3.
    Murphy-Chutorian, E., Trivedi, M.: Head pose estimation in computer vision: A survey. 31, 607–626 (2009)Google Scholar
  4. 4.
    Orozco, J., Gong, S.: Head pose classification in crowded scenes. In: British Machine Vision Conference (2009)Google Scholar
  5. 5.
    Brown, L., Tian, Y.: Comparative study of coarse head pose estimation. In: IEEE Workshop on Motion and Video Processing (2002)Google Scholar
  6. 6.
    Saul, L.K., Roweis, S.T.: Think globally, fit locally: unsupervised learning of low dimensional manifolds. Journal of Machine Learning Research 4, 119–155 (2003)CrossRefMathSciNetGoogle Scholar
  7. 7.
    Burges, C.J.C.: Geometric Methods for Feature Extraction and Dimensional Reduction. In: Book, Kluwer Academic Publishers, Dordrecht (2005)Google Scholar
  8. 8.
    van der Maaten, L., Postma, E., van den Herik, H.: Dimensionality reduction: A comparative review. Technical Report TiCC-TR 2009-005, Tilburg University (2009)Google Scholar
  9. 9.
    Raytchev, B., Yoda, I., Sakaue, K.: Head pose estimation by nonlinear manifold learning. In: ICPR, pp. 462–466 (2004)Google Scholar
  10. 10.
    Geng, X., Chuan Zhan, D., Hua Zhou, Z.: Supervised nonlinear dimensionality reduction for visualization and classification. IEEE Transactions on Systems, Man, and Cybernetics: Part B 35, 1098–1107 (2005)CrossRefGoogle Scholar
  11. 11.
    Fu, Y., Huang, T.S.: Graph embedded analysis for head pose estimation. In: FGR, pp. 3–8 (2006)Google Scholar
  12. 12.
    Sugiyama, M.: Local fisher discriminant analysis for supervised dimensionality reduction. In: International Conference on Machine learning, pp. 905–912 (2006)Google Scholar
  13. 13.
    Sugiyama, M.: Dimensionality reduction of multimodal labeled data by local fisher discriminant analysis. Journal of Machine Learning Research 8, 1027–1061 (2007)Google Scholar
  14. 14.
    Wang, X., Huang, X., Gao, J., Yang, R.: Illumination and person-insensitive head pose estimation using distance metric learning. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 624–637. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  15. 15.
    He, X., Ji, M., Bao, H.: Graph embedding with constraints. In: IJCAI, pp. 1065–1070 (2009)Google Scholar
  16. 16.
    Yang, M.H.: Extended isomap for pattern classification. In: ICPR (2002)Google Scholar
  17. 17.
    He, X., Yan, S., Hu, Y., Niyogi, P., Zhang, H.J.: Face recognition using laplacianfaces. PAMI 27, 328–340 (2005)Google Scholar
  18. 18.
    Chen, H.T., Chang, H.W., Liu, T.L.: Local discriminant embedding and its variants. In: CVPR, pp. 846–853 (2005)Google Scholar
  19. 19.
    Zhao, Q., Zhang, D., Lu, H.: Supervised LLE in ICA space for facial expression recognition. In: International Conference on Neural Networks and Brain, pp. 1970–1975 (2005)Google Scholar
  20. 20.
    Teoh, A.B.J., Pang, Y.H.: Analysis on supervised neighborhood preserving embedding. IEICE Electronics Express 6, 1631–1637 (2009)CrossRefGoogle Scholar
  21. 21.
    Nilsson, J., Sha, F., Jordan, M.I.: Regression on manifolds using kernel dimension reduction. In: International Conference on Machine Learning, pp. 697–704 (2007)Google Scholar
  22. 22.
    Balasubramanian, V.N., Ye, J., Panchanathan, S.: Biased manifold embedding: a framework for person-independent head pose estimation. In: CVPR (2007)Google Scholar
  23. 23.
    Balasubramanian, V.N., Krishna, S., Panchanathan, S.: Person-independent head pose estimation using biased manifold embedding. Eurasip Journal on Advances in Signal Processing 2008, 1–15 (2008)Google Scholar
  24. 24.
    He, X., Cai, D., Yan, S., Zhang, H.J.: Neighborhood preserving embedding. In: ICCV, pp. 1208–1213 (2005)Google Scholar
  25. 25.
    He, X., Niyogi, P.: Locality preserving projections. Advances in Neural Information Processing Systems 16, 100–200 (2004)Google Scholar
  26. 26.
    Little, G., Krishna, S., Black, J., Panchanthan, S.: A methodology for evaluating robustness of face recognition algorithms with respect to variations in pose angle and illumination angle. In: International Conference on Acoustics, Speech, and Signal Processing (2005)Google Scholar
  27. 27.
    Yan, S., Xu, D., Zhang, B., Zhang, H.J., Yang, Q., Lin, S.: Graph embedding and extensions: A general framework for dimensionality reduction. PAMI 29, 40–51 (2007)Google Scholar
  28. 28.
    Belkin, M., Niyogi, P.: Laplacian eigenmaps for dimensionality reduction and data representation. Journal of Neural Computation 15, 1373–1396 (2003)zbMATHCrossRefGoogle Scholar
  29. 29.
    Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290, 2323–2326 (2000)CrossRefGoogle Scholar
  30. 30.
    Zeng, X., Luo, S.: A supervised subspace learning algorithm: Supervised neighborhood preserving embedding. In: International Conference on Advanced Data Mining and Applications (2007)Google Scholar
  31. 31.
    de Ridder, D., Kouropteva, O., Okun, O., Pietikùinen, M., Duin, R.P.: Supervised locally linear embedding. In: International Conference on Artificial Neural Networks and Neural Information Processing (2003)Google Scholar
  32. 32.
    Li, C.G., Guo, J.: Supervised isomap with explicit mapping. In: Innovative Computing, Innovation, and Control (2006)Google Scholar
  33. 33.
    Tenenbaum, J.B., Silva, V., Langford, J.C.: A global geometric framework for nonlinear dimensionality reduction. Science 290, 2319–2323 (2000)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Chiraz BenAbdelkader
    • 1
  1. 1.New York Institute of TechnologyAbu DhabiUnited Arab Emirates

Personalised recommendations