Advertisement

Statistical Template Matching under Geometric Transformations

  • Alexander Sibiryakov
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4992)

Abstract

We present a novel template matching framework for detecting geometrically transformed objects. A template is a simplified representation of the object of interest by a set of pixel groups of any shape, and the similarity between the template and an image region is derived from the F-test statistic. The method selects a geometric transformation from a discrete set of transformations, giving the best statistical independence of such groups Efficient matching is achieved using 1D analogue of integral images - integral lines, and the number of operations required to compute the matching score is linear with template size, comparing to quadratic dependency in conventional template matching. Although the assumption that the geometric deformation can be approximated from discrete set of transforms is restrictive, we introduce an adaptive subpixel refinement stage for accurate matching of object under arbitrary parametric 2D-transformation. The parameters maximizing the matching score are found by solving an equivalent eigenvalue problem. The methods are demonstrated on synthetic and real-world examples and compared to standard template matching methods.

Keywords

Object Location Image Patch Template Match Integral Image Geometric Transformation 
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.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. IEEE CVPR, 511–518 (2001)Google Scholar
  2. 2.
    Sibiryakov, A., Bober, M.: A Method of Statistical Template Matching and Applications to Face and Facial Feature Detection, WSEAS Trans. on Information Science and Applications (September 2005)Google Scholar
  3. 3.
    Jain, A., Zhong, Y., Lakshmanan, S.: Object Matching Using Deformable Templates. IEEE TPAMI 18(3), 267–278 (1996)Google Scholar
  4. 4.
    Yoshimura, S., Kanade, T.: Fast template matching based on the normalized correlation by using multiresolution eigenimages. In: IEEE/RSJ/GI Int. Conf. on Intelligent Robots and Systems (IROS 1994), vol. 3, pp. 2086–2093 (1994)Google Scholar
  5. 5.
    Jones, M., Viola, P.: Fast Multi-view Face Detection. IEEE CVPR (June 2003)Google Scholar
  6. 6.
    Lienhart, R., Maydt, J.: An extended set of Haar-like features for rapid object detection. In: ICIP 2002, vol. 1, pp. 900–903 (2002)Google Scholar
  7. 7.
    Messom, C.H., Barczak, A.L.: Fast and Efficient Rotated Haar-like Features using Rotated Integral Images. In: Australasian Conf. on Robotics and Automation (2006)Google Scholar
  8. 8.
    Golub, G., Van Loan, C.: Matrix computations. Johns Hopkins University Press, Baltimore (1996), ISBN: 0-8018-5414-8Google Scholar
  9. 9.
    Gould, N., Leyffer, S.: An introduction to algorithms for nonlinear optimization. In: Blowey, J.F., Craig, A.W., Shardlow, T. (eds.) Frontiers in Numerical Analysis, pp. 109–197. Springer, Berlin (2003)Google Scholar
  10. 10.
    Lucas, B., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Proc. of Imaging understanding workshop, pp. 121–130 (1981)Google Scholar
  11. 11.
    Zitova, B., Flusser, J.: Image Registration Methods: a Survey. Image and Vision Computing 24, 977–1000 (2003)CrossRefGoogle Scholar
  12. 12.
    Choi, M.-S., Kim, W.-Y.: A novel two stage template matching method for rotation and illumination invariance. Pattern recognition 35(1), 119–129 (2002)zbMATHCrossRefGoogle Scholar
  13. 13.
    Tanaka, K., Sano, M., Ohara, S., Okudaira, M.: A parametric template method and its application to robust matching. IEEE CVPR, 620–627 (2000)Google Scholar
  14. 14.
    Zheltov, S., Sibiryakov, A.: Adaptive Subpixel Cross-Correlation in a Point Correspondence Problem. In: Gruen, A., Kuhbler, O. (eds.) Optical 3D Measurement Techniques, Zurich, September 29 - October 2, pp. 86–95 (1997)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Alexander Sibiryakov
    • 1
  1. 1.Mitsubishi Electric ITE-BVGuildfordUnited Kingdom

Personalised recommendations