Skip to main content
SpringerLink
Log in

Correspondence of coplanar features through P2-invariant representations

  • Statistics
  • Conference paper
  • First Online:
Applications of Invariance in Computer Vision (AICV 1993)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 825))

Abstract

An algorithm for establishing the correspondence between two projectively transformed sets of coplanar points (or lines) is proposed and its performance analyzed. Five-tuples of features are represented by projective/permutation (p2) invariants which are insensitive to the order of the features in the computation. Matched five-tuples yield feature correspondence hypotheses accumulated in a contingency table. The final correspondence is extracted from the table by a greedy algorithm. Positional uncertainties of up to five pixels and the presence of outliers are tolerated.

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

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Berger, M.: Geometry I, Springer, Berlin, 1987.

    Google Scholar 

  2. Grimson, W. E. L., Huttenlocher, D. P.: On the sensitivity of geometric hashing, Proceedings of the Third International Conference on Computer Vision, Osaka, Japan (December 1990) 334–338.

    Google Scholar 

  3. Grimson, W. E. L., Huttenlocher, D. P., Jacobs, D. W.: A study of affine matching with bounded sensor error, Computer Vision-ECCV '92, G. Sandini (Ed.), Springer, Berlin (1992) 292–306.

    Google Scholar 

  4. Forsyth, D., Mundy, J. L., Zisserman, A., Coelho, C., Heller, A.: Invariant descriptors for 3-D object recognition and pose, IEEE Trans. Pattern Anal. Mach. Intell., 13 (1991) 971–991.

    Google Scholar 

  5. Fulton, W., Harris, J.: Representation Theory, Graduate Texts in Mathematics (Vol. 129), Springer, Heidelberg, 1991.

    Google Scholar 

  6. Hartshorne, R.: Algebraic Geometry, Springer, New York, Corrected third printing, 1983.

    Google Scholar 

  7. Lamdan, Y., Schwartz, J. T., Wolfson, H. J.: Affine invariant model-based object recognition, IEEE Trans. Robot. Autom., 6 (1990) 578–589.

    Google Scholar 

  8. Lamdan, Y., Wolfson, H. J.: On the error analysis of ‘Geometric Hashing', Proceedings of the 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Lahaina, Maui, Hawaii (June 1991) 22–27.

    Google Scholar 

  9. Lenz, R., Meer, P.: Projection and permutation invariant object recognition, Proceedings of the 8th Scandinavian Conference on Image Analysis (May 1993) 389–396. Accepted for publication, Pattern Recognition.

    Google Scholar 

  10. Kanatani, K.: Computational projective geometry, CVGIP: Image Understanding, 54 (1991) 333–348.

    Google Scholar 

  11. Maybank, S. J.: The projection of two non-coplanar conics, 105–119 in [15].

    Google Scholar 

  12. Maybank, S. J.: Classification based on the cross ratio, Applications of Invariance in Computer Vision II. Proceedings of the Second European-US Workshop on Invariance, Ponta Delgada, Azores (October 1993) 113–132 (in this volume).

    Google Scholar 

  13. Meer, P., Weiss, I.: Point/line correspondence under 2D projective transformation, Proceedings of the 11th International Conference on Pattern Recognition: Computer Vision and Applications, The Hague, The Netherlands (September 1992) 399–402.

    Google Scholar 

  14. Morin, L.: Quelques contributions des invariants projectifs a la vision par ordinateur. PdD Thesis, Institut National Polytechnique de Grenoble, January 1993.

    Google Scholar 

  15. Mundy, J. L., Zisserman, A., editors: Geometric Invariance in Machine Vision, MIT Press, Cambridge, Mass, 1992.

    Google Scholar 

  16. Rothwell, C. A., Zisserman, A., Mundy, J. L., Forsyth, D. A.: Efficient model library access by projective invariant indexing functions, Proceedings of the 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Champaign, Illinois (June 1992) 109–114.

    Google Scholar 

  17. Shapiro, L. S., Brady, J. M.: Feature-based correspondence: an eigenvector approach, Image and Vision Computing, 10 (1992) 283–288.

    Google Scholar 

  18. Scott, G. L., Longuet-Higgins, H. C.: An algorithm for associating the features of two images, Proc. R. Soc. Lond. B, 244 (1991) 21–26.

    Google Scholar 

  19. Wayner, P. C.: Efficiently using invariant theory for model-based matching, Proceedings of the 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Lahaina, Maui, Hawaii (June 1991) 473–478.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Electrical and Computer Engineering, Rutgers University, P.O. Box 909, 08855-0909, Piscataway, NJ, USA

    Peter Meer & Sudhir Ramakrishna

  2. Image Processing Laboratory, Department of Electrical Engineering, Linköping University, S-58183, Linköping, Sweden

    Reiner Lenz

Authors
  1. Peter Meer
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sudhir Ramakrishna
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Reiner Lenz
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Joseph L. Mundy Andrew Zisserman David Forsyth

Rights and permissions

Reprints and permissions

Copyright information

© 1994 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Meer, P., Ramakrishna, S., Lenz, R. (1994). Correspondence of coplanar features through P2-invariant representations. In: Mundy, J.L., Zisserman, A., Forsyth, D. (eds) Applications of Invariance in Computer Vision. AICV 1993. Lecture Notes in Computer Science, vol 825. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-58240-1_25

Download citation

  • DOI: https://doi.org/10.1007/3-540-58240-1_25

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-58240-3

  • Online ISBN: 978-3-540-48583-4

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation