A Model-Based Method for Face Shape Recovery

  • William A. P. Smith
  • Edwin R. Hancock
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3522)


In this paper we describe a model-based method for recovering the 3D shape of faces using shape-from-shading. Using range-data, we learn a statistical model of the variation in surface normal direction for faces. This model uses the azimuthal equidistant projection to represent the distribution of surface normal directions. We fit the model to intensity data using constraints on the surface normal direction provided by Lambert’s law. We illustrate the effectiveness of the method on real-world image data.


Training Image Azimuth Angle Image Brightness Photometric Stereo Light Source Direction 
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.
    Johnston, A., Hill, H., Carman, N.: Recognising faces: effects of lighting direction, inversion, and brightness reversal. Perception 21, 365–375 (1992)CrossRefGoogle Scholar
  2. 2.
    Gregory, R.L.: Knowledge in perception and illusion. Phil. Trans. R. Soc. Lond. B 352, 1121–1128 (1997)CrossRefGoogle Scholar
  3. 3.
    Georghiades, A., Belhumeur, P., Kriegman, D.: From few to many: Illumination cone models for face recognition under variable lighting and pose. IEEE Trans. PAMI 23, 643–660 (2001)Google Scholar
  4. 4.
    Atick, J.J., Griffin, P.A., Redlich, A.N.: Statistical approach to shape from shading: Reconstruction of 3D face surfaces from single 2D images. Neural Comp. 8, 1321–1340 (1996)CrossRefGoogle Scholar
  5. 5.
    Zhao, W.Y., Chellappa, R.: Illumination-insensitive face recognition using symmetric shapefrom- shading. In: Proc. CVPR (2000)Google Scholar
  6. 6.
    Samaras, D., Metaxas, D.: Illumination constraints in deformable models for shape and light direction estimation. IEEE Trans. PAMI 25, 247–264 (2003)Google Scholar
  7. 7.
    Castelán, M., Hancock, E.R.: Acquiring height maps of faces from a single image. In: Proc. 3DPVT, pp. 183–190 (2004)Google Scholar
  8. 8.
    Prados, E., Faugeras, O.D.: Unifying approaches and removing unrealistic assumptions in shape from shading: Mathematics can help. In: Proc. ECCV, pp. 141–154 (2004)Google Scholar
  9. 9.
    Worthington, P.L., Hancock, E.R.: New constraints on data-closeness and needle map consistency for shape-from-shading. IEEE Trans. PAMI 21, 1250–1267 (1999)Google Scholar
  10. 10.
    Snyder, J.P.: Map Projections–AWorkingManual, U.S.G.S. Professional Paper 1395. United States Government Printing Office, Washington D.C. (1987)Google Scholar
  11. 11.
    Sirovich, L.: Turbulence and the dynamics of coherent structures. Quart. Applied Mathematics XLV, 561–590 (1987)MathSciNetGoogle Scholar
  12. 12.
    Blanz, V., Vetter, T.: A morphable model for the synthesis of 3d faces. In: Computer Graphics Proc. SIGGRAPH, pp. 187–194 (1999)Google Scholar
  13. 13.
    Frankot, R.T., Chellappa, R.: A method for enforcing integrability in shape from shading algorithms. IEEE Trans. PAMI 10, 439–451 (1988)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • William A. P. Smith
    • 1
  • Edwin R. Hancock
    • 1
  1. 1.Department of Computer ScienceThe University of York 

Personalised recommendations