Advertisement

Hypothesis verification in model-based object recognition with a gaussian error model

  • Frédéric Jurie
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1407)

Abstract

The use of hypothesis verification is recurrent in the model based recognition literature. Small sets of features forming salient groups are paired with model features. Poses can be hypothesised from this small set of feature-to-feature correspondences. The verification of the pose consists in measuring how much model features transformed by the computed pose coincide with image features. When data involved in the initial pairing are noisy the pose is inaccurate and the verification is a difficult problem.

In this paper we propose a robust hypothesis verification algorithm, assuming data error is Gaussian. Previous approaches using gaussian error model start from an initial set of correspondences and try to extend it feature by feature. This solution is not optimal. In this paper, the opposite strategy is adopted. Assuming the right pose belongs to a known volume of the pose space (including the initial pose) we take into account all of the correspondences compatible with this volume and refine iteratively this set of correspondences. This is our main contribution. We present experimental results obtained with 2D recognition proving that the proposed algorithm is fast and robust.

Keywords

Model-Based Recognition Pose Verification 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    T.D. Alter and D.W. Jacobs. Error propagation in full 3d from 2d object recognition. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 892–898, Seatle, Washington, 1994.Google Scholar
  2. 2.
    J.R. Beveridge and E.M. Riseman. Optimal geometric model matching under full 3d perspective. Computer Vision and Image Understanding, 61(3):351–364, 1995.CrossRefGoogle Scholar
  3. 3.
    T.M. Breuel. Fast recognition using adaptive subdivisions of transformation space. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 445–451, Champain, Illinois, 1992.Google Scholar
  4. 4.
    R. Brunelli and D. Falavigna. Person identification using multiple cues. IEEE Transactions on Pattern Analysis and Machine Intelligence, 17(10):955–966, October 1995.CrossRefGoogle Scholar
  5. 5.
    A.C. Califano and R. Mohan. Mulidimensional indexing for recognizing visual shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 16(4):373–392, April 1994.CrossRefGoogle Scholar
  6. 6.
    R. Fletcher. Practical Methods of Optimization. John Wiley and Sons, New York, wiley-interscience publications edition, 1987.Google Scholar
  7. 7.
    T.L. Gandhi and O.I. Camps. Robust feature selection for object recognition using uncertain 2d image data. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 281–287, Seatle, Washington, 1994.Google Scholar
  8. 8.
    D.M. Gavrila and F.C.A. Groen. 3d object recognition from 2d images using geometric hashing. Pattern Recognition Letters, 13:263–278, 1992.CrossRefGoogle Scholar
  9. 9.
    W.E.L. Grimson. The combinatorics of heuristic search term for object recognition in cluttered environment. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(9):920–935, September 1991.MathSciNetCrossRefGoogle Scholar
  10. 10.
    W.E.L Grimson, D.P. Huttenlocher, and D.W. Jacobs. A study of affine matching with bounded sensor error. In Proc. European Conference on Computer Vision, pages 291–306, Santa Margherita Ligure, Italy, 1992.Google Scholar
  11. 11.
    D.P. Huttenlocher and T.A. Cass. Measuring the quality of hypotheses in model-based recognition. In Proc. European Conference on Computer Vision, pages 773–777, Santa Margherita Ligure, Italy, 1992.Google Scholar
  12. 12.
    D.P Huttenlocher, G.A. Klanderman, and W.J Rucklidge. Comparing images using the hausdorff distance. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(9):850–863, 1993.CrossRefGoogle Scholar
  13. 13.
    D.W. Jacobs. Robust and efficient detection of salient convex groups. 18(1):541–548, January 1996.Google Scholar
  14. 14.
    H. Murase and S.K. Nayar. Visual learning and recognition od 3d object from appearance. International Journal of Computer Vision, 18(14):5–24, 1995.CrossRefGoogle Scholar
  15. 15.
    C.F. Olson. Time and space efficient pose clustering. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 251–258, Seatle, Washington, 1994.Google Scholar
  16. 16.
    A.P. Pentland, B. Moghadam, and T. Starner. View-based and modular eigenspaces for face recognition. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 84–91, Seatle, Washington, 1994.Google Scholar
  17. 17.
    K.B. Sarachik and W.E.L. Grimson. Gaussian error models for object recognition. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 400–406, New-York, 1993.Google Scholar
  18. 18.
    S. Sclaroff and A.P. Pentland. Modal matching for correspondence and recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 17:545–561, 6 1995.CrossRefGoogle Scholar
  19. 19.
    B.M. ter Haar Romeny, L.M.J. Florack, A.H. Salden, and M.A. Viergever. Higher order differential structure of images. Image and Vision Computing, 12(6):317–325, 1994.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Frédéric Jurie
    • 1
  1. 1.LASMEA - CNRS UMR 6602Université Blaise-PascalAubièreFrance

Personalised recommendations