Shape And Texture-Based Deformable Models For Facial Image Analysis

  • Stan Z. Li
  • Zhen Lei
  • Ying Zheng
  • Zeng-Fu Wang
Part of the Topics in Biomedical Engineering. International Book Series book series (ITBE)

In this chapter we introduce concepts and algorithms of shape- and texture-based deformable models — more specifically Active Shape Models (ASMs), Active Appearance Models (AAMs), and Morphable Models — for facial image analysis. Such models, learned from training examples, allow admissible deformations under statistical constraints on the shape and/or texture of the pattern of interests. As such, the deformation is in accordance with the specific constraints on the pattern. Based on analysis of problems with the standard ASM and AAM, we further describe enhanced models and algorithms, namely Direct Appearance Models (DAMs) and a Texture-ConstrainedASM(TC-ASM), for improved fitting of shapes and textures. A method is also described for evaluation of goodness of fit using an ASM. Experimental results are provided to compare different methods.


Face Image Training Image Appearance Model Landmark Point Active Appearance Model 
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 TF, Taylor CJ, Cooper DH, Graham J. 1995. Active shape models: their training and application. Comput Vision Image Understand 61:38-59.CrossRefGoogle Scholar
  2. 2.
    Cootes TF, Edwards GJ, Taylor CJ. 1998. Active appearance models. In Proceedings of the European conference on computer vision, Vol. 2, pp. 484-498. Ed. H Burkhardt, B Neumann. New York: Springer.Google Scholar
  3. 3.
    Edwards GJ, Cootes TF, Taylor CJ. 1998. Face recognition using active appearance models. In Proceedings of the European conference on computer vision, Vol. 2, pp. 581-695. Ed. H Burkhardt, B Neumann. New York: Springer.Google Scholar
  4. 4.
    Cootes TF, Taylor CJ.2001. Statistical models of appearance for computer vi- sion. Technical Report, Wolfson Image Analysis Unit, Manchester University,
  5. 5.
    Sclaroff S, Isidoro J. 1998. Active blobs. In Proc IEEE Int Conf Comput Vision, Bombay, India, pp. 1146-1153.Google Scholar
  6. 6.
    Cootes TF, Walker KN, Taylor CJ. 2000. View-based active appearance models. In 4th Interna-tional conference on automatic face and gesture recognition, Grenoble, France, pp. 227-232.
  7. 7.
    Psarrou A, Romdhani S, Gong S. 1999. Learning a single active face shape model across views. In Proceedings of the IEEE international workshop on recognition, analysis, and tracking of faces and gestures in real-time systems, Corfu, Greece, 26-27 September, pp. 31-38. Washington, DC: IEEE Computer Society.Google Scholar
  8. 8.
    Cootes TF, Taylor CJ. 2001. Constrained active appearance models. Proc IEEE Int Conf Comput Vision 1:748-754.Google Scholar
  9. 9.
    Blanz V, Vetter T. 1999. A morphable model for the synthesis of 3D faces. In Proc. Siggraph’99, pp. 187-194. New York: ACM Press.Google Scholar
  10. 10.
    Li Y, Gong S, Liddell H. 2001. Constructing facial identity surfaces in a nonlinear discriminat-ing space. Proc IEEE Comput Soc Conf: Computer Vision and Pattern Recognition 2:258-263.Google Scholar
  11. 11.
    Duta N, Jain AK, Dubuisson-Jolly M. 2001. Automatic construction of 2D shape models. IEEE Trans Pattern Analy Machine Intell 23(5):433-446.CrossRefGoogle Scholar
  12. 12.
    van Ginneken B, Frangi AF, Staal JJ, ter Haar Romeny BM, Viergever MA. 2001. A nonlinear gray-level appearance model improves active shape model segmentation. In IEEE workshop on mathematical models in biomedical image analysis, pp. 205-212. Ed. L Staib, A Rangarajan. Washington, DC: IEEE Society Press.CrossRefGoogle Scholar
  13. 13.
    Baker S, Matthews I. 2001. Equivalence and efficiency of image alignment algorithms. Proc IEEE Conf Comput Vision Pattern Recognition 1:1090-1097.Google Scholar
  14. 14.
    Ahlberg J. 2001. Using the active appearance algorithm for face and facial feature tracking. In IEEE ICCV workshop on recognition, analysis and tracking of faces and gestures in real-time systems, Vancouver, Canada, July 13, 2001, pp. 68-72. Washington, DC: IEEE.CrossRefGoogle Scholar
  15. 15.
    Hou XW, Li SZ, Zhang HJ, Cheng QS. 2001. Direct appearance models. Proc IEEE Conf Comput Vision Pattern Recognition 1:828-833.Google Scholar
  16. 16.
    Li SZ, Yan SC, Zhang HJ, Cheng QS. 2002. Multi-view face alignment using direct appearance models. Proc 5th Int Conf Automatic Face Gesture Recogn, Washington, DC, 20-21 May 2002, pp. 309-314. Washington, DC: IEEE.Google Scholar
  17. 17.
    Yan SC, Liu C, Li SZ, Zhang HJ, Shum H, Cheng QS. 2003. Face alignment using texture-constrained active shape models. Image Vision Comput 21(1):69-75.CrossRefGoogle Scholar
  18. 18.
    XS Huang, SZ Li, YS Wang. 2004. Statistical learning of evaluation function for ASM/AAM im-age alignment. In Proceedings: Biometric Authentication, ECCV 2004 International Workshop, BioAW 2004, Prague, Czech Republic, May 15, 2004 (ECCV Workshop BioAW), pp. 45-56. Ed D Maltoni, AK Jain. New York: Springer.Google Scholar
  19. 19.
    Cootes TF, Edwards GJ, Taylor CJ. 1999. Comparing active shape models with active appearance models. In 10th British Machine Vison Conference, Vol. 1, pp. 173-182. Ed. T Pridmore, D Elli-man. Nottingham, UK: BMVA Press.
  20. 20.
    Basso C, Romdhani S, Blanz V, Vetter T. 2005. Morphable models of faces. In Handbook of face recognition, pp. 217-245. Ed S Li, A Jain. New York: Springer.Google Scholar
  21. 21.
    Blanz V, Vetter T. 2003. Face recognition based on fitting a 3D morphable model. IEEE Trans Pattern Anal Machine Intell 25(9):1063-1074.CrossRefGoogle Scholar
  22. 22.
    Jones MJ, Poggio T. 1998. Multidimensional morphable models. Proc IEEE Int Conf Comput Vision, pp. 683-688.
  23. 23.
    Bergen JR, Hingorani R. 1990. Hierarchical motion-based frame rate conversion. Technical Report, David Sarnoff Research Center, Princeton, NJ.Google Scholar
  24. 24.
    Li S, Zhang ZQ, Zhu L, Zhang HJ. 2002. Real-time multi-view face detection. In Proc 5th Int Conf Automatic Face Gesture Recogn, Washington, DC, 20-21 May 2002, pp. 149-154. Washington, DC: IEEE.Google Scholar
  25. 25.
    Schapire RE, Singer Y. 1999. Improved boosting algorithms using confidence-rated predictions. Machine Learning 37(3):297-299.MATHCrossRefGoogle Scholar
  26. 26.
    Friedman J, Hastie T, Tibshirani R. 2000. Additive logistic regression: a statistical view of boosting. Ann Stat 28(2):337-374.MATHCrossRefMathSciNetGoogle Scholar
  27. 27.
    Viola P, Jones M. 2001. Robust real-time object detection. Int J Comput Vision. To appear.Google Scholar
  28. 28.
    Friedman JH. 2001. Greedy function approximation: a gradient boosting machine. Ann Stat, 29(5):1189-1232.MATHCrossRefGoogle Scholar
  29. 29.
    Mason L, Baxter J, Bartlett PL, Frean M. 1999. Functional gradient techniques for combining hypotheses. In Advances in large margin classifiers, pp. 221-247. Ed. AJ Smola, PL Bartlett, B Sch ölkopf, D Schuurmans. Cambridge: MIT Press.Google Scholar
  30. 30.
    Zemel RS, Pitassi T. 2001. A gradient-based boosting algorithm for regression problems. In Advances in neural information processing systems, Vol. 13. Ed. TK Leen, TG Dietterich, V Tresp. Cambridge: MIT Press.
  31. 31.
    Schapire RE, Freund Y, Bartlett P, Lee WS. 1998. Boosting the margin: a new explanation for the effectiveness of voting methods. Ann Stat 26(5):1651-1686.MATHCrossRefMathSciNetGoogle Scholar
  32. 32.
    Freund Y, Schapire RE. 1997. A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55(1):119-139.MATHCrossRefMathSciNetGoogle Scholar
  33. 33.
    Martinez AM, Benavente R. 1998. The AR face database. Computer Vision Center Technical Report No. 24. Barcelona, Spain.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2007

Authors and Affiliations

  • Stan Z. Li
    • 1
  • Zhen Lei
    • 1
  • Ying Zheng
    • 2
  • Zeng-Fu Wang
    • 2
  1. 1.National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesChina
  2. 2.Department of Automation, Institute of Information Science and TechnologyUniversity of Science and Technology of ChinaChina

Personalised recommendations