Advertisement

Very Fast Template Matching

  • H. Schweitzer
  • J. W. Bell
  • F. Wu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2353)

Abstract

Template matching by normalized correlations is a common technique for determine the existence and compute the location of a shape within an image. In many cases the run time of computer vision applications is dominated by repeated computation of template matching, applied to locate multiple templates in varying scale and orientation. A straightforward implementation of template matching for an image size n and a template size k requires order of kn operations. There are fast algorithms that require order of n log n operations. We describe a new approximation scheme that requires order n operations. It is based on the idea of “Integral-Images”, recently introduced by Viola and Jones.

Keywords

Normalize Correlation Polynomial Approximation Template Match Centralize Moment Integral Image 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Rosenfeld, A., Kak, A.C.: Digital Picture Processing. Second edn. Academic Press (1982)Google Scholar
  2. 2.
    Duda, R.O., Hart, P.E.: Pattern Classification and Scene Analysis. John Wiley & Sons (1973)Google Scholar
  3. 3.
    Winograd, S.: Arithmetic Complexity of Computation. Volume 33 of SIAM CBMS-NSF. SIAM, Philadelphia (1980)Google Scholar
  4. 4.
    Davis, L., Bajcsy, R., Herman, M., Nelson, R.: RSTA on the move: Detection and tracking of moving objects from an autonomous mobile platform. In: Proceedings of the ARPA Image Understanding Workshop, Palm Springs, CA (1996) 651–664Google Scholar
  5. 5.
    Armstrong, J.B., Maheswaran, M., Theys, M.D., Siegel, H.J., Nichols, M.A., Casey, K.H.: Parallel image correlation: Case study to examine trade-offs in algorithm-to-machine mappings. The Journal of Supercomputing 12 (1998) 7–35zbMATHCrossRefGoogle Scholar
  6. 6.
    Fang, Z., Li, X., Ni, L.M.: Parallel algorithms for image template matching on hypercube SIMD computers. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-9 (1987) 835–841CrossRefGoogle Scholar
  7. 7.
    Goshtasby, A., Gage, S.H., Bartholic, J.F.: A two-stage cross correlation approach to template matching. IEEE Transactions on Pattern Analysis and Machine Intelligence 6 (1984) 374–378CrossRefGoogle Scholar
  8. 8.
    Rosenfeld, A., Vanderburg, G.J.: Coarse-fine template matching. IEEE Transactions on Systems, Man, and Cybernetics (1977) 104–107Google Scholar
  9. 9.
    Yoshimura, S., Kanade, T.: Fast template matching based on the normalized correlation by using multiresolution eigenimages. In: International Conference on Intelligent Robots and Systems, Munchen, Germany (1994) 2086–2093Google Scholar
  10. 10.
    Viola, P., Jones, M.: Robust real-time object detection. Presented in the Second International Workshop on Statistical and Computational Theories of Vision, ICCV’2001 (2001) http://www.ai.mit.edu/people/viola/research/publications/ICCV01-Viola-Jones.ps.gz.

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • H. Schweitzer
    • 1
    • 2
  • J. W. Bell
    • 1
    • 2
  • F. Wu
    • 1
    • 2
  1. 1.The University of Texas at DallasRichardsonUSA
  2. 2.Voxar AGPlanoUSA

Personalised recommendations