International Journal of Computer Vision

, Volume 8, Issue 2, pp 99–111 | Cite as

Feature extraction from faces using deformable templates

  • Alan L. Yuille
  • Peter W. Hallinan
  • David S. Cohen


We propose a method for detecting and describing features of faces using deformable templates. The feature of interest, an eye for example, is described by a parameterized template. An energy function is defined which links edges, peaks, and valleys in the image intensity to corresponding properties of the template. The template then interacts dynamically with the image by altering its parameter values to minimize the energy function, thereby deforming itself to find the best fit. The final parametr values can be used as descriptors for the feature. We illustrate this method by showing deformable templates detecting eyes and mouths in real images. We demonstrate their ability for tracking features.


Image Processing Artificial Intelligence Computer Vision Feature Extraction Computer Image 
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. Ayache, N., Boissonnat, J.D., Brunet, E., Cohen, L., Chieze, J.P., Geiger, B., Monga, O., Rocchisani, J.M., and Sander, P. 1989. Building highly structured volume representations in 3D medical images, Comp. Assoc. Rad., Proc. Intern. Symp., Berlin, pp. 765–772.Google Scholar
  2. Ballard, D.H., and Brown, C.M., 1982. Computer Vision Prentice-Hall: Englewood Cliffs, NJ.Google Scholar
  3. Bennett, A., and Craw, I., 1991. Finding image features for deformable templates and detailed prior statistical knowledge. Preprint. Dept. Mathematical Sciences, University of Aberdeen. Scotland.Google Scholar
  4. Brunelli, R., 1991. Face recognition: Dynamic programming for the detection of face outline, Technical Report 910–06, Instituto per la Ricerca Scientifica e Tecnologica, Trento, Italy.Google Scholar
  5. Burr, D.J., 1981a. A dynamic model for image registration, Comput. Graph. Image Process. 15:102–112.Google Scholar
  6. Burr, D.J., 1981b. Elastic matching of line drawings, IEEE Trans. Patt. Anal. Mach. Intell. 3(6):708–713.Google Scholar
  7. Durbin, R., and Willshaw, D.J., 1987. An analogue approach to the travelling salesman problem using an elastic net method, Nature. pp. 689–691.Google Scholar
  8. Durbin, R., Szeliski, R., and Yuille, A.L., 1989. An analysis of the elastic net approach to the travelling salesman problem, Neurol Computat. 1:348–358.Google Scholar
  9. Grenander, U., Chow, Y. and Keenan, D.M., 1991. HANDS. A Pattern Theoretical Study of Biological Shapes. Springer-Verlag: New York.Google Scholar
  10. Hallinan, P.W., 1991. Recognizing human eyes. Proc. Conf. 1570. SPIE San Diego.Google Scholar
  11. Huber, P.J., 1981. Robust Statistics. Wiley: New York.Google Scholar
  12. Kanade, T., 1977. Computer recognition of human faces, Birkhauser Verlag, Basel and Stuttgart.Google Scholar
  13. Kass, M., Witkin, A., and Terzopoulos, D., 1987. Snakes: Active contour models, Proc. 1st Intern. Conf. Comput. Vis. London, June.Google Scholar
  14. Lipson, P., Yuille, A.L., O'Keefe, D., Cavanaugh, J., Taaffe, J. and Rosenthal, D., 1990. Deformable templates for feature extraction from medical images. Proc. 1st Europ. Conf. Comput. Vis. Antibes, France.Google Scholar
  15. Maragos, P., 1987. Tutorial on advances in morphological image processing and analysis, Optical Engineering 26: 623–632, July.Google Scholar
  16. Parisi, G., 1988. Statistical Field Theory, Addison-Wesley: Reading, MA.Google Scholar
  17. Pentland, A., 1987. Recognition by parts. Proc. 1st Intern. Conf. Comput. Vis., London, June.Google Scholar
  18. Serra, J., 1982. Image, Analysis and Mathematical Morphology, Academic Press: New York.Google Scholar
  19. Shackleton, M.A., and Welsh, W.J. 1991. Classification of facial features for recognition Proc. Comput. Vis. Patt. Recog. Hawaii pp. 573–579.Google Scholar
  20. Yuille, A.L., Cohen, D.S., and Hallinan, P.W., 1989. Feature extraction from faces using deformable templates, Proc. Comput. Vis. Patt. Recog., pp. 104–109.Google Scholar
  21. Yuille, A.L., and Hallinan, P.W., 1992. Deformable templates, in Active Vision, ed. A.Blake and A.L.Yuille. M.I.T. Press: Cambridge, to appear.Google Scholar

Copyright information

© Kluwer Academic Publishers 1992

Authors and Affiliations

  • Alan L. Yuille
    • 1
  • Peter W. Hallinan
    • 1
  • David S. Cohen
    • 1
  1. 1.Division of Applied SciencesHarvard UniversityCambridgeUSA

Personalised recommendations