International Journal of Computer Vision

, Volume 33, Issue 2, pp 95–116 | Cite as

When is it Possible to Identify 3D Objects From Single Images Using Class Constraints?

  • Ronen Basri
  • Yael Moses


One approach to recognizing objects seen from arbitrary viewpoint is by extracting invariant properties of the objects from single images. Such properties are found in images of 3D objects only when the objects are constrained to belong to certain classes (e.g., bilaterally symmetric objects). Existing studies that follow this approach propose how to compute invariant representations for a handful of classes of objects. A fundamental question regarding the invariance approach is whether it can be applied to a wide range of classes. To answer this question it is essential to study the set of classes for which invariance exists. This paper introduces a new method for determining the existence of invariant functions for classes of objects together with the set of images from which these invariants can be computed. We develop algebraic tests that determine whether the objects in a given class can be identified from single images. These tests apply to classes of objects undergoing affine projection. In addition, these tests allow us to determine the set of views of the objects which are degenerate. We apply these tests to several classes of objects and determine which of them is identifiable and which of their views are degenerate.

object recognition class-based recognition viewpoint invariance 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Basri, R. 1996. Paraperspective ≡ affine. International Journal of Computer Vision, 19(2):169–180.Google Scholar
  2. Burns J.B., Weiss R.S., and Riseman, E.M. 1993. View variation of point-set and line-segment features. IEEE Trans. on Pattern Analysis and Machine Intelligence, 15(1):51–68.Google Scholar
  3. Clemens, D. and Jacobs, D. 1991. Space and time bounds on model indexing. IEEE Trans. on Pattern Analysis and Machine Intelligence, 13(10):1007–1018.Google Scholar
  4. Fischler, M.A. and Bolles, R.C. 1981. Random sample consensus: a paradigm for model fitting with application to image analysis and automated cartography. Com. of the A.C.M., 24(6):381–395.Google Scholar
  5. Faugeras, O.D. 1992. What can be seen in three dimensions with an uncalibrated stereo rig? In Second European Conf. on Computer Vision, pp. 563–378.Google Scholar
  6. Fawcett, R., Zisserman, A., and Brady, J.M. 1994. Extracting structure from an affine view of a 3D point set with one or two bilateral symmetries. Image and Vision Computing, 12(9):615–622.Google Scholar
  7. Forsyth, D., Mundy, J.L., Zisserman, A., Coelho, C., Heller, A., and Rothwell, C. 1991. Invariant descriptors for 3-D object recognition and pose. IEEE Trans. on Pattern Analysis and Machine Intelligence, 13(10):971–991.Google Scholar
  8. Hartley, R.I. 1993. Invariants of lines in spaces, In Proc. of DARPA Image Understanding Workshop, pp. 737–744.Google Scholar
  9. Hartley, R.I. 1994. Projective reconstruction and invariants from multiple images. IEEE Trans. on Pattern Analysis and Machine Intelligence, 16(10):1036–1041.Google Scholar
  10. Huttenlocher, D.P. and Ullman, S. 1990 "Recognizing Solid Objects by Alignment with an Image, Int. J. Computer Vision, 5(2):195–212.Google Scholar
  11. Jacobs, D. 1992. Space efficient 3D model indexing. In IEEE Conf. on Computer Vision and Pattern Recognition, pp. 439–444.Google Scholar
  12. Jones, M.J. and Poggio, T. 1995. Model-Based Matching of Line Drawings by Linear Combinations of Prototypes. In International Conference on Computer Vision, pp. 531–536Google Scholar
  13. Koenderink, J. and van Doorn, A. 1991. Affine structure from motion. Journal of the Optical Society of America, 8(2):377–385.Google Scholar
  14. Lamdan, Y. and Wolfson, H.J. 1988. Geometric Hashing: A General and Efficient Model-Based Recognition Scheme. In Second International Conference on Computer Vision, pp. 238–249.Google Scholar
  15. Lowe, D. 1985. Perceptual Organization and Visual Recognition. Kluwer Academic Publishers: The Netherlands.Google Scholar
  16. Mitsumoto, H., Tamura, S., Okazaki, K., Kajimi, N., and Fukui, Y. 1992. 3-D reconstruction using mirror images based on a plane symmetry recovering method. IEEE Trans. on Pattern Analysis and Machine Intelligence, 14(9):941–946.Google Scholar
  17. Moses, Y. and Ullman, S. 1992. Limitations of non model-based recognition schemes. In Second European Conf. on Computer Vision, pp. 820–828.Google Scholar
  18. Mundy, J.L. and Zisserman, A. 1994. Repeated structures: image correspondence constraints and 3D structure recovery. In Applications of Invariance in Computer Vision, J.L. Mundy, A. Zisserman and D.A. Forsyth (Eds.), Lecture Notes in Computer Science, Vol. 825, Springer-Verlag.Google Scholar
  19. Poggio, T. and Vetter, T. 1992. Recognition and structure from one 2D model view: observations on prototypes, object classes and symmetries. M.I.T., A.I. Memo No. 1347.Google Scholar
  20. Quan, L. 1995. "Invariants of six points and projective reconstruction from three uncalibrated images. IEEE Trans. on Pattern Analysis and Machine Intelligence, 17(1):34–46.Google Scholar
  21. Quan, L. 1996. Conic reconstruction and correspondence from two views." IEEE Trans. on Pattern Analysis and Machine Intelligence, 18(2):151–160.Google Scholar
  22. Rothwell, C.A. 1995. Object Recognition through Invariant Indexing. Oxford University Press, Oxford, UK.Google Scholar
  23. Rothwell, C.A., Zisserman, A., Forsyth, D.A., and Mundy, J.L. 1992. Canonical Frames for Planar Object Recognition. In Proc. of 2nd European Conf. on Computer Vision, pp. 757–772.Google Scholar
  24. Sparr, G. 1992. Depth Computations from Polyhedral Images. Image and Vision Computing, 10:683–688.Google Scholar
  25. Sugimoto, A. 1994. Geometric invariant of noncoplanar lines in a single view. In Proc. of Int. Conference on Pattern Recognition, 1:190–195.Google Scholar
  26. Thompson, D.W. and Mundy, J.L. 1987. Three dimensional model matching from an unconstrained viewpoint. In Proc. of IEEE Int. Conf. on robotics and Automation, pp. 208–220.Google Scholar
  27. Tomasi, C. and Kanade, T. 1992. Shape and Motion from Image Streams under Orthography: a Factorization Method. International Journal of Computer Vision, 9(2):137–154.Google Scholar
  28. Ullman, S. and Basri, R. 1991. Recognition by linear combinations of models. IEEE Trans. on Pattern Analysis and Machine Intelligence, 13(10):992–1006.Google Scholar
  29. Weiss, I. 1988. Projective invariants of shape. DARPA Image Understanding Workshop, pp. 1125–1134.Google Scholar
  30. Weinshall D. 1993. Model-based invariants for 3D vision," International Journal of Computer Vision, 10(1):27–42.Google Scholar
  31. Weinshall, D. and Werman, M. 1997. On view likelihood and stability. IEEE Trans. on Pattern Analysis and Machine Intelligence, 19(2):97–108.Google Scholar
  32. Werman, M. and Shashua, A. 1995. The study of 3D-from-2D using elimination. Fifth International Conference Computer Vision, pp. 473–479.Google Scholar
  33. Yan, X., Peng, J.X., Ding, M.Y., and Xue, D.H. 1997. The unique solution of projective invariants of 6 points from 4 uncalibrated images. Pattern Recognition, 30(3):513–517.Google Scholar
  34. Zisserman, A., Forsyth, D., Mundy, J., Rothwell, C., Liu, J., and Pillow, N. 1995. 3D object recognition using invariance. Artificial Intelligence, 78:239–288.Google Scholar

Copyright information

© Kluwer Academic Publishers 1999

Authors and Affiliations

  • Ronen Basri
    • 1
  • Yael Moses
    • 1
  1. 1.Department of Computer ScienceThe Weizmann Institute of ScienceRehovotIsrael

Personalised recommendations