Skip to main content
SpringerLink
Log in

What Is the Set of Images of an Object Under All Possible Illumination Conditions?

  • Published:
International Journal of Computer Vision Aims and scope Submit manuscript

Abstract

The appearance of an object depends on both the viewpoint from which it is observed and the light sources by which it is illuminated. If the appearance of two objects is never identical for any pose or lighting conditions, then–in theory–the objects can always be distinguished or recognized. The question arises: What is the set of images of an object under all lighting conditions and pose? In this paper, we consider only the set of images of an object under variable illumination, including multiple, extended light sources and shadows. We prove that the set of n-pixel images of a convex object with a Lambertian reflectance function, illuminated by an arbitrary number of point light sources at infinity, forms a convex polyhedral cone in IRn and that the dimension of this illumination cone equals the number of distinct surface normals. Furthermore, the illumination cone can be constructed from as few as three images. In addition, the set of n-pixel images of an object of any shape and with a more general reflectance function, seen under all possible illumination conditions, still forms a convex cone in IRn. Extensions of these results to color images are presented. These results immediately suggest certain approaches to object recognition. Throughout, we present results demonstrating the illumination cone representation.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Bajcsy, R., Lee, S. and Leonardis, A. 1996. Detection of diffuse and specular interface reflections and inter-reflections by color image segmentation. Int. J. Computer Vision, 17(3):241-272.

    Google Scholar 

  • Belhumeur, P., Hespanha, J. and Kriegman, D. 1996. Eigenfaces vs. Fisherfaces: Recognition using class specific linear projection. In European Conf. on Computer Vision, pages 45-58.

  • Belhumeur, P. and Kriegman, D. 1996. What is the set of images of an object under all possible lighting conditions. In Proc. IEEE Conf. on Comp. Vision and Patt. Recog., pages 270-277.

  • Belhumeur, P., Kriegman, D. and Yuille, A. 1997. The bas-relief ambiguity. In IEEE Proc. Conf. Computer Vision and Pattern Recognition.

  • Binford, T. 1987. Generic surface interpretation: Observability model. In Proc. of the4th International Symposium on Robotics Research, Santa Cruz, CA.

  • Canon, M., Cullum Jr., C. and Polak, E. 1970. Theory of Optimal Control and Mathematical Programming. McGraw-Hill, New York.

    Google Scholar 

  • Epstein, R., Hallinan, P. and Yuille, A. 1994. 5 ± 2 Eigenimages suffice: An empirical investigation of low-dimensional lighting models. Technical Report 94-11, Harvard University.

  • Epstein, R., Yuille, A. and Belhumeur, P. 1996. Learning and recognizing objects using illumination subspaces. In Proc. of the Int. Workshop on Object Representation for Computer Vision.

  • Finlayson, G., Drew, M. and Funt, B. 1994. Spectral sharpening: Sensor transformations for improved color constancy. J. Opt. Soc. Am. A, 11:1553-1563.

    Google Scholar 

  • Forsyth, D. and Fleck, M. 1997. Body plans. In IEEE Proc. Conf. Computer Vision and Pattern Recognition.

  • Forsyth, D. and Zisserman, A. 1991. Reflections on shading. IEEE Trans. Pattern Anal. Mach. Intelligence, 13(7):671-679.

    Article  Google Scholar 

  • Hallinan, P. 1994. A low-dimensional representation of human faces for arbitrary lighting conditions. In Proc. IEEE Conf. on Comp. Vision and Patt. Recog., pages 995-999.

  • Hayakawa, H. 1994. Photometric stereo under a light-source with arbitrary motion. JOSA-A, 11(11):3079-3089.

    Google Scholar 

  • Horn, B. 1986. Computer Vision. MIT Press, Cambridge, Mass..

    Google Scholar 

  • Jacobs, D. 1997. Linear fitting with missing data: Applications to structure from motion and characterizing intensity images. In IEEE Proc. Conf. Computer Vision and Pattern Recognition.

  • Klinker, G., Shafer, S. and Kanade, T. 1988. Image segmentation and reflection analysis through color. Int. J. Computer Vision, 2(1):7-32.

    Google Scholar 

  • Koenderink, J. and van Doorn, A. 1996. Bidirectional reflection distribution function expressed in terms of surface scattering modes. In European Conf. on Computer Vision, II:28-39.

    Google Scholar 

  • Langer, M. and Zucker, S. 1995. A ray-based computational model of light sources and illumination. In Physics Based Modeling Workshop in Computer Vision, page SESSION 4.

  • Moses, Y., Adini, Y. and Ullman, S. 1994. Face recognition: The problem of compensating for changes in illumination direction. In European Conf. on Computer Vision, pages 286-296.

  • Murase, H. and Nayar, S. 1995. Visual learning and recognition of 3-D objects from appearence. Int. J. Computer Vision, 14:5-24.

    Google Scholar 

  • Nayar, S., Ikeuchi, K. and Kanade, T. 1991. Shape from interreflections. IJCV, 6(3):173-195.

    Google Scholar 

  • Nayar, S. and Murase, H. 1996. Dimensionality of illumination in appearance matching. IEEE Conf. on Robotics and Automation.

  • Oren, M. and Nayar, S. 1995. Generalization of the Lambertian model and implications for machine vision. Int. J. Computer Vision, 14:227-251.

    Google Scholar 

  • Pentland, A., Moghaddam, B. and Starner. 1994. View-based and modular eigenspaces for face recognition. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, pages 84-91.

  • Poggio, T. and Sung, K. 1994. Example-based learning for viewbased human face detection. In Proc. Image Understanding Workshop, II:843-850.

    Google Scholar 

  • Rockafellar, R. 1970. Convex Analysis. Princeton University Press, Princeton.

    Google Scholar 

  • Shashua, A. 1992. Geometry and Photometry in 3D Visual Recognition. PhD thesis, MIT.

  • Sirovitch, L. and Kirby, M. 1987. Low-dimensional procedure for the characterization of human faces. J. Optical Soc. of America A, 2:519-524.

    Google Scholar 

  • Tagare, H. and de Figueiredo, R. 1993. A framework for the construction of reflectance maps for machine vision. Comp. Vision, Graphics, and Image Proces., 57(3):265-282.

    Google Scholar 

  • Torrance, K. and Sparrow, E. 1967. Theory for off-specular reflection from roughened surfaces. JOSA, 57:1105-1114.

    Google Scholar 

  • Turk, M. and Pentland, A. 1991. Eigenfaces for recognition. J. of Cognitive Neuroscience, 3(1).

  • Ullman, S. and Basri, R. 1989. Recognition by a linear combination of models. A.I. Memo 1152, MIT.

Download references

Author information

Authors and Affiliations

  1. Center for Comp. Vision and Control, Dept. of Electrical Engineering, Yale University, New Haven, CT, 06520

    Peter N. Belhumeur & David J. Kriegman

Authors
  1. Peter N. Belhumeur
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. David J. Kriegman
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Belhumeur, P.N., Kriegman, D.J. What Is the Set of Images of an Object Under All Possible Illumination Conditions?. International Journal of Computer Vision 28, 245–260 (1998). https://doi.org/10.1023/A:1008005721484

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/A:1008005721484

Search

Navigation