A Constrained Hybrid Optimization Algorithm for Morphable Appearance Models

  • Cuiping Zhang
  • Fernand S. Cohen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3757)


In this paper, we propose a constrained hybrid optimization algorithm that incorporates several shape constraints into a gradient descent procedure using a novel unbiased cost function. Shape constraints are heuristically derived from face images where the face shape can be directly estimated based on ”motion” analysis. To better locate face contour points regardless of the background, local projection models are used. Experiments show that our algorithm benefits significantly from these shape constraints and achieves a much higher convergent rate compared to the inverse compositional optimization algorithm. We test our algorithm on different face databases, and demonstrate its robustness in presence of various illuminations, background patterns, as well as variations in face expressions.


Face Image Motion Estimation Face Database Face Shape Landmark Point 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Cootes, T., Edwards, G., Taylor, C.: Active appearance models. IEEE Trans. PAMI 23, 681–685 (2001)Google Scholar
  2. 2.
    Jones, M.J., Poggio, T.: Ultidimensional morphable models. In: Proc. of the International Conference on Computer Vision, pp. 683–688 (1998)Google Scholar
  3. 3.
    Matthews, I., Baker, S.: Active appearance models revisited. International Journal of Computer Vision 60 (2004)Google Scholar
  4. 4.
    Cootes, T.F., Kittipanya-ngam, P.: Comparing variations on the active appearance model algorithm. In: Proceedings of the British Machine Vision Conference, Cardiff, UK (2002)Google Scholar
  5. 5.
    Stegmann, M.: Active appearance models: Theory, extensions and cases. Master’s thesis, Department of Mathematical Modelling, Technical University of Denmark, Department of Mathematical Modelling, Lyngby, Denmark (2000)Google Scholar
  6. 6.
    Cootes, T., Taylor, C., Cooper, D., Graham, J.: Active shape models: Their training and application. CVGIP: Imaging Understanding 61, 38–59 (1995)CrossRefGoogle Scholar
  7. 7.
    Xu, X., Zhang, C., Huang, T.S.: Active morphable model: An efficient method for face analysis. In: Sixth IEEE International Conference on Automatic Face and Gesture Recognition, Seoul, Korea (2004)Google Scholar
  8. 8.
    Baker, S., Gross, R., Matthews, I.: Lucas-kanade 20 years on: A unifying framework: Part 2. Technical Report Technical Report CMU-RI-TR-03-01, Robotics Institude, Carnegie Mellon University (2004)Google Scholar
  9. 9.
    Zhang, C., Cohen, F.: Face shape extraction and recognition using 3d morphing and distance mapping. In: 4th IEEE International Conference on Automatic Face and Gesture Recognition, Grenoble, France (2000)Google Scholar
  10. 10.
    Phillips, P., Moon, H., Rauss, P., Rizvi, S.: The feret evaluation methodology for face recognition algorithms. In: Proceedings of IEEE Computer Vision and Pattern Recognition, pp. 137–143 (1997)Google Scholar
  11. 11.
    The phychological image collection at stirling,
  12. 12.
    Lyons, M.J., Akamatsu, S., Kamachi, M., Gyoba, J.: Coding facial expressions with gabor wavelets. In: Third IEEE International Conference on Automatic Face and Gesture Recognition, Nara, Japan, pp. 200–205 (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Cuiping Zhang
    • 1
  • Fernand S. Cohen
    • 1
  1. 1.Electrical and Computer Engineering departmentDrexel UniversityPhiladelphiaUSA

Personalised recommendations