Shape representations from shading primitives

  • John Haddon
  • David Forsyth
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1407)


Diffuse interreflections mean that surface shading and shape are related in ways that are difficult to untangle; in particular, distant and invisible surfaces may affect the shading field that one sees. The effects of distant surfaces are confined to relatively low spatial frequencies in the shading field, meaning that we can expect signatures, called shading primitives, corresponding to shape properties. We demonstrate how these primitives can be used to support the construction of useful shape representations. Approaches to this include testing hypotheses of geometric primitives for consistency with the shading field, and looking for shading events that are distinctive of some shape event. We show that these approaches can be composed, leading to an attractive process of representation that is intrinsically bottom up. This representation can be extracted from images of real scenes, and that the representation is diagnostic.


Support Vector Machine Spatial Frequency Body Segment IEEE Conf High Spatial Frequency 
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.


  1. 1.
    I. Biederman. Recognition-by-components: A theory of human image understanding. Psych. Review, 94(2):115–147, 1987.CrossRefGoogle Scholar
  2. 2.
    T. Binford. Visual perception by computer. In Proc. IEEE Conference on Systems and Control, 1971.Google Scholar
  3. 3.
    A. Blake. Boundary conditions for lightness computation in mondrian world. Computer Vision, Graphics and Image Processing, 32:314–327, 1985.CrossRefGoogle Scholar
  4. 4.
    J. Brady and H. Asada. Smoothed local symmetries and their implementation. International Journal of Robotics Research, 3(3), 1984.Google Scholar
  5. 5.
    C. Cortes and V. Vapnik. Support-vector networks. Machine Learning, 20(3):273–97, 1995.zbMATHGoogle Scholar
  6. 6.
    A. Dempster, N. Laird, and D. Rubin. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society B, 39, 1977.Google Scholar
  7. 7.
    D. Forsyth and M. Fleck. Body plans. In IEEE Conf. on Computer Vision and Pattern Recognition, 1997.Google Scholar
  8. 8.
    D. Forsyth, J. Malik, M. Fleck, and J. Ponce. Primitives, perceptual organisation and object recognition. in review.Google Scholar
  9. 9.
    D. Forsyth and A. Zisserman. Reflections on shading. IEEE T. Pattern Analysis and Machine Intelligence, 13(7):671–679, 1991.CrossRefGoogle Scholar
  10. 10.
    A. D. Gross and T. E. Boult. Recovery of shgcs from a single intensity view. IEEE T. Pattern Analysis and Machine Intelligence, 18(2):161–180, 1996.CrossRefGoogle Scholar
  11. 11.
    J. Haddon and D. Forsyth. Shading primitives: Finding folds and shallow grooves. In Int. Conf. on Computer Vision, 1998.Google Scholar
  12. 12.
    B. Horn. Shape from shading: a method for obtaining the shape of a smooth opaque object from one view. Ai tr-232, MIT, 1970.Google Scholar
  13. 13.
    B. Horn and M. Brooks. Shape from shading. MIT Press, 1989.Google Scholar
  14. 14.
    B. K. P. Horn. Determining lightness from an image. Computer Vision, Graphics and Image Processing, 3:277–299, 1974.Google Scholar
  15. 15.
    J. Koenderink. Vignetting and reflexes. Shading Course Notes.Google Scholar
  16. 16.
    J. Koenderink and A. V. Doom. Geometrical modes as a method to treat diffuse interreflections in radiometry. J. Opt. Soc. Am., 73(6):843–850, 1983.Google Scholar
  17. 17.
    E. Land and J. McCann. Lightness and retinex theory. J. Opt. Soc. Am., 61(1):1–11, 1971.CrossRefGoogle Scholar
  18. 18.
    M. Langer and S. Zucker. Shape-from-shading on a cloudy day. Journal of the Optical Society of America A, 11(2):467–78.Google Scholar
  19. 19.
    M. Langer and S. Zucker. Diffuse shading, visibility fields, and the geometry of ambient light. In IEEE Conf. on Computer Vision and Pattern Recognition, pages 18–47, 1993.Google Scholar
  20. 20.
    D. Marr and K. Nishihara. Representation and recognition of the spatial organization of three-dimensional shapes. Proc. Royal Society, London, B-200:269–294, 1978.CrossRefGoogle Scholar
  21. 21.
    S. Nayar, K. Ikeuchi, and T. Kanade. Shape from interreflections. IJCV, 6(3):173–195, August 1991.CrossRefGoogle Scholar
  22. 22.
    R. Nevatia and T. Binford. Description and recognition of complex curved objects. Artificial Intelligence, 8:77–98, 1977.zbMATHCrossRefGoogle Scholar
  23. 23.
    M. Oren, C. Papageorgiou, P. Sinha, and E. Osuna. Pedestrian detection using wavelet templates. In IEEE Conf. on Computer Vision and Pattern Recognition, pages 193–9, 1997.Google Scholar
  24. 24.
    E. Osuna, R. Freund, and F. Girosi. Training support vector machines: an application to face detection. In IEEE Conf. on Computer Vision and Pattern Recognition, pages 130–6, 1997.Google Scholar
  25. 25.
    J. Shi and J. Malik. Normalized cuts and image segmentation. In IEEE Conf. on Computer Vision and Pattern Recognition, 1997.Google Scholar
  26. 26.
    unknown. Pose file 6. unknown, unknown. A collection of photographs of human models, annotated in Japanese.Google Scholar
  27. 27.
    T. Wada, H. Ukida, and T. Matsuyama. Shape from shading with interreflections under proximal light source-3d shape reconstruction of unfolded book surface from a scanner image. In Int. Conf. on Computer Vision, pages 66–71, 1995.Google Scholar
  28. 28.
    R. Woodham. Photometric method for determining surface orientation from multiple images. Optical Engineering, 19(1):139–44, 1980.Google Scholar
  29. 29.
    J. Yang, N. Ohnishi, D. Zhang, and N. Sugie. Determining a polyhedral shape using interreflections. In IEEE Conf. on Computer Vision and Pattern Recognition, pages 110–115, 1997.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • John Haddon
    • 1
  • David Forsyth
    • 1
  1. 1.Computer Science DivisionUniversity of CaliforniaBerkeley

Personalised recommendations