Skip to main content
SpringerLink
Log in

A Coarse-to-Fine Method for Shape Recognition

  • Short Paper
  • Published:
Journal of Computer Science and Technology Aims and scope Submit manuscript

Abstract

In this paper the deformation invariant curve matching problem is addressed. The proposed approach exploits an image pyramid to constrain correspondence search at a finer level with those at a coarser level. In comparison to previous methods, this approach conveys much richer information: curve topology, affine geometry and local intensity are combined together to seek correspondences. In experiments, the method is tested in two applications, contour matching and shape recognition, and the results show that the approach is effective under perspective and articulated deformations.

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

  1. Asada H, Brady M. The curvature primal sketch. IEEE Trans. Pattern Analysis and Machine Intelligence, 1986, 8(1): 2–14.

    Google Scholar 

  2. Gdalyahu Y, Weinshall D. Flexible syntactic matching of curves and its application to automatic Hierarchical Classification of Silhouettes. IEEE Trans. Pattern Analysis and Machine Intelligence, 1999, 21(12): 1312–1328.

    Article  Google Scholar 

  3. Shen D, Wong W, Ip H H S. Affine-invariant image retrieval by correspondence matching of shape. Image and Vision Computing, 1999, 17(7): 489–499.

    Article  Google Scholar 

  4. Gottschalk P G, Turney J L, Mudge T N. Efficient recognition of partially visible objects using a logarithmic complexity matching technique. The International Journal of Robotics Research, 1999, 8(2): 110–131.

    Google Scholar 

  5. Han M H, Jang D. The use of maximum curvature points for the recognition of partially occluded objects. Pattern Recognition, 1990, 23(1): 21–33.

    Article  Google Scholar 

  6. Tsai W H, Yu S S. Attributed string matching with merging for shape recognition. IEEE Trans. Pattern Analysis and Machine Intelligence, 1985, 7(4): 453–462.

    Article  Google Scholar 

  7. Ayache N, Faugeras O D. HYPER: A new approach for the recognition and positioning of two-dimensional objects. IEEE Trans. Pattern Analysis and Machine Intelligence, 1986, 8(1): 44–54.

    Google Scholar 

  8. Xue Z, Shen D, Teoh E K. An efficient fuzzy algorithm for aligning shapes under affine transformations. Pattern Recognition, 2001, 34(6): 1171–1180.

    Article  MATH  Google Scholar 

  9. Hartley R I, Zisserman A. Multiple View Geometry in Computer Vision. Cambridge University Press, 2004, pp. 87–127.

  10. Faugeras O. What can be seen in three dimensions with an uncalibrated stereo rig. In Proc. European Conf. Computer Vision, Santa Margherita Ligure, Italy, May 19–22, 1992, pp. 563–578.

  11. Hartley R I, Gupta R, Chang T. Stereo from uncalibrated cameras. In Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition, Champaign, USA, June 15–18, 1992, pp. 761–764.

  12. Orrite C, Blecua S, Herrero J E. Shape matching of partially occluded curves invariant under projective transformation. Computer Vision and Image Understanding, 2004, 93: 34–64.

    Article  Google Scholar 

  13. Rivlin E, Weiss I. Local invariants for recognition. IEEE Trans. Pattern Analysis and Machine Intelligence, 1995, 17(3): 226–238.

    Article  Google Scholar 

  14. Rattarangsi A, Chin R T. Scale-based detection of corners of planar curves. IEEE Trans. Pattern Analysis and Machine Intelligence, 1992, 14(4): 430–449.

    Article  Google Scholar 

  15. Mokhtarian F, Mackworth A K. A theory of multi-scale, curvature-based shape representation for planar curves. IEEE Trans. Pattern Analysis and Machine Intelligence, 1992, 14(8): 789–805.

    Article  Google Scholar 

  16. Forsyth D A, Ponce J. Computer Vision: A Modern Approach. Prentice Hall, 2002, pp. 475–476.

  17. Marr D, Poggio T. A computational theory of human stereo vision. In Proc. the Royal Society of London, 1979, B(204): 301–328.

    Google Scholar 

  18. Cohen F S, Huang Z, Yang Z. Invariant matching and identification of curves using B-spline curve representation. IEEE Trans. Image Processing, 1995, 4(1): 1–10.

    Article  Google Scholar 

  19. Pajdla T, Van Gool L. Matching of 3-D curves using semi-differential invariants. In Proc. IEEE Int. Conf. Computer Vision, Cambridge, Massachusetts, USA, June 20–23, 1995, pp. 390–395.

  20. Rogers D F, Adams J A. Mathematical Elements for Computer Graphics, 2nd Edition. New York: McGraw-Hill, 1990, pp. 305–339.

    Google Scholar 

  21. Knuth D E. The Art of Computer Programming. Addison-Wesley, 1973, pp. 73–168.

  22. Ferrari V, Tuytelaars T, Gool L V. Widebaseline multiple-view correspondence. In Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition, Madison, WI, USA, June 16–22, 2003, 1: 718–725.

  23. Murase H, Nayar S. Visual learning and recognition of 3-D objects from appearance. International Journal on Computer Vision, 1995, 14(1): 5–24.

    Article  Google Scholar 

  24. Sonka M, Hlavac V, Boyle R. Image Processing, Analysis and Machine Vision. Chapman & Hall, 1993, pp. 442–448.

  25. Greiner G, Seidel H P. Modeling with triangular B-splines. IEEE Graphics and Applications, 1994, 14(2): 56–60.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, Fudan University, Shanghai, 200433, China

    Hui-Xuan Tang & Hui Wei

  2. Shanghai Laboratory of Intelligent Information Processing, Fudan University, Shanghai, 200433, China

    Hui-Xuan Tang & Hui Wei

Authors
  1. Hui-Xuan Tang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hui Wei
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hui-Xuan Tang.

Additional information

Supported by the National Natural Science Foundation of China under Grant No.60303007 and the National Grand Fundamental Research 973 Program of China under Grant No. 2001CB309401.

Electronic supplementary material

Rights and permissions

Reprints and permissions

About this article

Cite this article

Tang, HX., Wei, H. A Coarse-to-Fine Method for Shape Recognition. J Comput Sci Technol 22, 330–334 (2007). https://doi.org/10.1007/s11390-007-9040-8

Download citation

  • Received:

  • Revised:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11390-007-9040-8

Keywords

Search

Navigation