Advertisement

Invariants for recovering shape from shading

  • Isaac Weiss
Foundations
Part of the Lecture Notes in Computer Science book series (LNCS, volume 825)

Abstract

The image formed by shading depends on many variables, including the shape of the object, the lighting characteristics, the imaging system, etc. Most of these variables are not known in advance, so the calculation of shape from shading is difficult. The problem could be greatly simplified if we could find invariants of the situation, namely quantities that stay constant as some of the unknown variables change. In this paper we apply known methods of mathematical physics to finding invariants of physical imaging processes. These methods take advantage of various symmetries, which can be part of a model-based approach to recognition. We concentrate on the shape from shading problem, but the methods have a much wider applicability.

Keywords

Characteristic Curve Surface Reflectance Initial Curve Legendre Transformation Invariant Equation 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Horn, B.K.P.: Robot Vision, MIT Press (1986)Google Scholar
  2. Lovelock, D. and Rund, H.: Tensors, Differential Forms, and Variational Principles, Dover (1975)Google Scholar
  3. Mundy, J.L. and Zisserman, A., Eds: Geometric Invariance in Machine Vision, MIT Press (1992)Google Scholar
  4. Oliensis, J. and Dupuis, P.: Provably convergent algorithms for shape from shading. Proc. DARPA Image Understanding Workshop, Washington, D.C. (April 1993) 1121–1130Google Scholar
  5. Weiss, I.: Projective invariants of shapes. Proc. DARPA Image Understanding Workshop, Cambridge, MA (April 1988) 1125–1134Google Scholar
  6. Weiss, I.: Noise resistance invariants of curves. IEEE T-PAMI 15 (Sept. 1992) 943–948Google Scholar
  7. Weiss, I.: Geometric invariants and object recognition. International Journal of Computer Vision 10:3 (June 1993) 201–231Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • Isaac Weiss
    • 1
  1. 1.Center for Automation ResearchUniversity of MarylandCollege ParkUSA

Personalised recommendations