Face Alignment Via Component-Based Discriminative Search

  • Lin Liang
  • Rong Xiao
  • Fang Wen
  • Jian Sun
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5303)

Abstract

In this paper, we propose a component-based discriminative approach for face alignment without requiring initialization. Unlike many approaches which locally optimize in a small range, our approach searches the face shape in a large range at the component level by a discriminative search algorithm. Specifically, a set of direction classifiers guide the search of the configurations of facial components among multiple detected modes of facial components. The direction classifiers are learned using a large number of aligned local patches and misaligned local patches from the training data. The discriminative search is extremely effective and able to find very good alignment results only in a few (2~3) search iterations. As the new approach gives excellent alignment results on the commonly used datasets (e.g., AR [18], FERET [21]) created under-controlled conditions, we evaluate our approach on a more challenging dataset containing over 1,700 well-labeled facial images with a large range of variations in pose, lighting, expression, and background. The experimental results show the superiority of our approach on both accuracy and efficiency.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Avidan, S.: Support vector tracking. IEEE Trans. on PAMI 26(8), 1064–1072 (2004)Google Scholar
  2. 2.
    Blake, A., Isard, M.: Active Contours. Springer, London (1998)Google Scholar
  3. 3.
    Chen, H., Xu, Y.-Q., Shum, H.-Y., Zhu, S.-C., Zheng, N.-N.: Example-based facial sketch generation with non-parametric sampling, vol. 2, pp. 433–438 (2001)Google Scholar
  4. 4.
    Cootes, T., Edwards, G., Taylor, C.: Active appearance models. In: Burkhardt, H., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1407. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  5. 5.
    Cootes, T.F., Taylor, C.J.: Constrained active appearance models. In: ICCV, vol. I, pp. 748–754 (2001)Google Scholar
  6. 6.
    Cootes, T.F., Taylor, C.J., Graham, J.: Active shape models – their training and application. Computer Vision and Image Understanding 61, 38–59 (1995)CrossRefGoogle Scholar
  7. 7.
    Cootes, T.F., Taylor, C.J.: A mixture model for representing shape variation. Image and Vision Computing 17(8), 567–574 (1999)CrossRefGoogle Scholar
  8. 8.
    Cootes, T.F., Walker, K., Taylor, C.J.: View-based active appearance models. Automatic Face and Gesture Recognition, 227–232 (2000)Google Scholar
  9. 9.
    Cristinacce, D., Cootes, T.F.: Boosted regression active shape models, vol. 2, pp. 880–889 (2007)Google Scholar
  10. 10.
    Cui, J., Wen, F., Xiao, R., Tang, X.: Easyalbum: An interactive photo annotation system based on face clustering and re-ranking. In: SIGCHI (2007)Google Scholar
  11. 11.
    Gu, L., Kanade, T.: 3d alignment of face in a single image, vol. 1, pp. 1305–1312 (2006)Google Scholar
  12. 12.
    Hou, X., Li, S.Z., Zhang, H., Cheng, Q.: Direct appearance models, vol. I, pp. 828–833 (2001)Google Scholar
  13. 13.
    Huang, G.B., Ramesh, M., Berg, T., Miller, E.L.: Labeled faces in the wild: A database for studying face recognition in unconstrained environments. Technical Report, 25(12):07–49 (October 2007)Google Scholar
  14. 14.
    Li, Y., Ai, H., Yamashita, T., Lao, S., Kawade, M.: Tracking in low frame rate video: A cascade particle filter with discriminative observers of different lifespans. In: CVPR, pp. 1–8 (2007)Google Scholar
  15. 15.
    Liang, L., Wen, F., Xu, Y., Tang, X., Shum, H.-Y.: Accurate face alignment using shape constrained markov network. In: CVPR 2006 (2006)Google Scholar
  16. 16.
    Liu, C., Shum, H.-Y., Zhang, C.: Hierarchical shape modeling for automatic face localization. In: ECCV, pp. 687–703 (2002)Google Scholar
  17. 17.
    Liu, X.: Generic face alignment using boosted appearance model. In: CVPR 2007 (2007)Google Scholar
  18. 18.
    Martinez, A.M., Benavente, R.: The ar face database. CVC Technical Report (24) (1998)Google Scholar
  19. 19.
    Matthews, I., Baker, S.: Active appearance models revisited. IJCV 60(2), 135–164 (2004)CrossRefGoogle Scholar
  20. 20.
    Blake, A., Williams, O., Cipolla, R.: Sparse bayesian learning for efficient visual tracking. IEEE Trans. on PAMI 27(8), 1292–1304 (2005)Google Scholar
  21. 21.
    Phillips, P.J., Moon, H., Rauss, P.J., Rizvi, S.: The feret evaluation methodology for face recognition algorithms. IEEE Trans. on PAMI 22(10), 1090–1104 (2000)Google Scholar
  22. 22.
    Romdhani, S., Cong, S., Psarrou, A.: A multi-view non-linear active shape model using kernel pca. In: BMVC 1999 (1999)Google Scholar
  23. 23.
    Sim, T., Baker, S., Bsat, M.: The cmu pose, illumination, and expression database. IEEE Trans. on PAMI 25(12), 1615–1618 (2003)Google Scholar
  24. 24.
    Tu, J., Zhang, Z., Zeng, Z., Huang, T.: Face localization via hierarchical condensation with fisher boosting feature selection. In: CVPR, vol. 2, pp. 719–724 (2004)Google Scholar
  25. 25.
    Viola, P., Jones, M.J.: Robust real-time face detection. In: IJCV, vol. 57(2), pp. 137–154 (2004)Google Scholar
  26. 26.
    Wiskott, L., Fellous, J.M., Krüger, N., von der Malsburg, C.: Face recognition by elastic bunch graph matching. In: ICIP 1997 (1997)Google Scholar
  27. 27.
    Yuille, A.L., Cohen, D.S., Hallinan, P.W.: Feature extraction from faces using deformable templates. In: CVPR, pp. 104–109.Google Scholar
  28. 28.
    Zhou, Y., Gu, L., Zhang, H.-J.: Bayesian tangent shape model: Estimating shape and pose parameters via bayesian inference. In: CVPR, vol. 1, pp. 109–116 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Lin Liang
    • 1
  • Rong Xiao
    • 1
  • Fang Wen
    • 1
  • Jian Sun
    • 1
  1. 1.Microsoft Research AsiaBeijingChina

Personalised recommendations