Advertisement

Convergence of model based shape from shading

  • Michael S. Lew
  • Michel Chaudron
  • Nies Huijsmans
  • Alfred She
  • Thomas S. Huang
Poster Session B: Active Vision, Motion, Shape, Stereo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1310)

Abstract

Three dimensional models are used by a wide variety of applications such as face recognition and model based coding for teleconferencing. In face recognition and model based coding the generic 3D model is used to generate images of the individual from any viewpoint. Recent work has been focussed on using shape from shading for refinement of the generic model toward the 3D shape of the individual. However, the previous methods have been based on iteration schemes in which convergence could not be proven. The main goal of this paper is to introduce a provably convergent algorithm for solving the problem of model based shape from shading. Bounds on the number of iterations for attaining error of order h are also given.

Keywords

Face Recognition Real Image Gradient Vector Variational Calculus Laser Range Finder 
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.

References

  1. Ballard, D. and C. M. Brown, Computer Vision, Prentice-Hall, Englewood Cliffs, New Jersey, 1982.Google Scholar
  2. Courant, R. and D. Hilbert, Methods of Mathematical Physics, vol. 1, Interscience Publishers, New York, 1953.Google Scholar
  3. Horn, B. K. P., “Obtaining Shape from Shading Information,” Psychology of Machine Vision, McGraw-Hill, New York, pp. 115–155, 1975.Google Scholar
  4. Ikeuchi, K., “Shape from Regular Patterns — An Example of Constraint Propagation in Vision,” Proceedings of the Fifth International Joint Conference on Pattern Recognition, Miami Beach, Florida, 1980.Google Scholar
  5. Ikeuchi, K., and B. K. P. Horn, “Numerical Shape from Shading and Occluding Boundaries,” Artificial Intelligence, vol. 17, pp. 141–184, 1981.Google Scholar
  6. Isaacson, E., and H. B. Keller, Analysis of Numerical Methods, John Wiley & Sons, New York, 1966.Google Scholar
  7. Lee, David, “A Provable Convergent Algorithm for Shape From Shading,” Shape From Shading edited by Horn and Brooks, MIT Press, Cambridge, pp. 349–373.Google Scholar
  8. Lew, M., A. C. She and T. S. Huang, “Intermediate Views For Face Recognition,” Lecture Notes in Computer Science: Proceedings of the 6th International Conference on Computer Analysis of Images and Patterns, pp. 138–145, 1995.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Michael S. Lew
    • 1
  • Michel Chaudron
    • 1
  • Nies Huijsmans
    • 1
  • Alfred She
    • 2
  • Thomas S. Huang
    • 2
  1. 1.Computer Science Dept.Leiden UniversityRA LeidenNetherlands
  2. 2.Electrical Engineering Dept.University of IllinoisUrbanaUSA

Personalised recommendations