Enhanced GPT Correlation for 2D Projection Transformation Invariant Template Matching

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9358)

Abstract

This paper describes a newly enhanced technique of 2D projection transformation invariant template matching, GPT (Global Projection Transformation) correlation. The key ideas are threefold. First, we show that arbitrary 2D projection transformation (PT) with a total of eight parameters can be approximated by a simpler expression. Second, using the simpler PT expression we propose an efficient computational model for determining sub-optimal eight parameters of PT that maximize a normalized cross-correlation value between a PT-superimposed input image and a template. Third, we obtain optimal eight parameters of PT via the successive iteration method. Experiments using templates and their artificially distorted images with random noise as input images demonstrate that the proposed method is far superior to the former GPT correlation method. Moreover, k-NN classification of handwritten numerals by the proposed method shows a high recognition accuracy through its distortion-tolerant template matching ability.

Keywords

Distortion-tolerant template matching 2D projection transformation Normalized cross-correlation 

Notes

Acknowledgments

A part of this work was supported by JSPS KAKENHI Grant Numbers 26330207 and 26280054.

References

  1. 1.
    Ouyang, W., Tombari, F., Mattoccia, S., Stefano, L.D., Cham, W.-K.: Performance evaluation of full search equivalent pattern matching algorithms. IEEE Trans. Pattern Anal. Machine Intell. 34(2), 127–143 (2012)CrossRefGoogle Scholar
  2. 2.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60(2), 91–110 (2004)CrossRefGoogle Scholar
  3. 3.
    Morel, J.M., Yu, G.: Asift: A new framework for fully affine invariant image comparison. SIAM J. Imaging Sci. 2(2), 438–469 (2009)MathSciNetCrossRefMATHGoogle Scholar
  4. 4.
    Jiang, H., Yu, S.X.: Linear solution to scale and rotation invariant object matching. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2474–2481. IEEE Press, New York (2009)Google Scholar
  5. 5.
    Li, H., Huang, X., He, L.: Object matching using a locally affine invariant and linear programming techniques. IEEE Trans. Pattern Anal. Machine Intell. 35(2), 411–424 (2013)CrossRefGoogle Scholar
  6. 6.
    Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Proceedings of 7th International Joint Conference on Artificial Intelligence, pp. 674–679. IEEE Press, New York (1981)Google Scholar
  7. 7.
    Baker, S., Matthews, I.: Lucas-Kanade 20 years on: a unifying framework. Int. J. Comput. Vision 56(3), 221–255 (2004)CrossRefGoogle Scholar
  8. 8.
    Korman, S., Reichman, Tsur, D.G., Avidan, S.: FAsT-Match: fast affine template matching. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2331–2338. IEEE Press, New York (2013)Google Scholar
  9. 9.
    Simard, P., LeCun, Y., Denker, J.: Efficient pattern recognition using a new transformation distance. In: Proceedings of Advances in Neural Information Processing Systems 5, pp. 50–58. Morgan Kaufmann Publishers Inc., San Francisco (1992)Google Scholar
  10. 10.
    Ha, T.M., Bunke, H.: Off-line, handwritten numeral recognition by perturbation method. IEEE Trans. Pattern Anal. Machine Intell. 19(5), 535–539 (1997)CrossRefGoogle Scholar
  11. 11.
    Ronee, M., Uchida, S., Sakoe, H.: Handwritten character recognition using piecewise linear two-dimensional warping. In: Proceedings of Sixth International Conference on Document Analysis and Recognition, pp. 39–43. The IEEE Computer Society, Los Alamitos (2001)Google Scholar
  12. 12.
    Wakahara, T., Kimura, Y., Tomono, A.: Affine-invariant recognition of gray-scale characters using global affine transformation correlation. IEEE Trans. Pattern Anal. Machine Intell. 23(4), 384–395 (2001)CrossRefGoogle Scholar
  13. 13.
    Wakahara, T., Yamashita, Y.: GPT correlation for 2D projection transformation invariant template matching. In: Proceedings of 22nd International Conference on Pattern Recognition, pp. 3810–3815. The IEEE Computer Society, Los Alamitos (2014)Google Scholar
  14. 14.
    Osuga, K., Tsutsumida, T., Yamaguchi, S., Nagata, K.: IPTP survey on handwritten numeral recognition. IPTP Research and Survey Report R-96-V-02, The Ministry of Posts and Telecommunications (1996) (in Japanese)Google Scholar
  15. 15.
    Iijima, T.: Pattern Recognition. Corona, Tokyo (1973). (in Japanese)Google Scholar
  16. 16.
    The Mathematical Society of Japan, Ito, K.: Encyclopedic Dictionary of Mathematics, 2nd edn. The MIT Press, Cambridge (1987)Google Scholar
  17. 17.
    Shi, M., Fujisawa, Y., Wakabayashi, T., Kimura, F.: Handwritten numeral recognition using gradient and curvature of gray scale image. Pattern Recogn. 35, 2051–2059 (2002)CrossRefMATHGoogle Scholar
  18. 18.
    Casey, R.G.: Moment normalization of handprinted characters. IBM J. Res. Develop. 14, 548–557 (1970)CrossRefMATHGoogle Scholar
  19. 19.
    Wakahara, T., Yamashita, Y.: \(k\)-NN classification of handwritten characters via accelerated GAT correlation. Pattern Recogn. 47, 994–1001 (2014)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Open Access This chapter is distributed under the terms of the Creative Commons Attribution Noncommercial License, which permits any noncommercial use, distribution, and reproduction in any medium, provided the original author(s) and source are credited.

Authors and Affiliations

  1. 1.Faculty of Computer and Information SciencesHosei UniversityKoganei-shiJapan
  2. 2.Graduate School of Engineering and ScienceTokyo Institute of TechnologyMeguro-kuJapan

Personalised recommendations