Advertisement

Optimal Pixel Matching between Images

  • Yuichi Yaguchi
  • Kenta Iseki
  • Ryuichi Oka
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5414)

Abstract

A two-dimensional continuous dynamic programming (2DCDP) method is proposed for two-dimensional spotting recognition of images. Spotting recognition is simultaneous segmentation and recognition of an image by optimal pixel matching between a reference and an input image. The proposed method performs optimal pixel-wise image matching and two-dimensional pixel alignment, which are not available in conventional algorithms. Experimental results show that 2DCDP precisely matches the pixels of non-linearly deformed images.

Keywords

Optimal Pixel Matching DP Spotting Image Registration Segmentation 

References

  1. 1.
    Forsyth, D., Ponce, J.: Computer Vision: A Modern Approach. Prentice Hall Professional Technical Reference, Englewood Cliffs (2002)Google Scholar
  2. 2.
    Brunelli, R., Poggio, T.: Face recognition: features versus templates. IEEE Trans. on PAMI 15(10), 1042–1052 (1993)CrossRefGoogle Scholar
  3. 3.
    Geiger, D., Gupta, A., Costa, L., Vlontzos, J.: Dynamic programming for detecting, tracking, and matching deformable contours. IEEE Trans. on PAMI 17(3), 294–302 (1995)CrossRefGoogle Scholar
  4. 4.
    Zitová, B., Flusser, J.: Image registration methods: a survey. Image and Vision Computing 21(11), 977–1000 (2003)CrossRefGoogle Scholar
  5. 5.
    Pluim, J., Maintz, J., Viergever, M.: Mutual-information-based registration of medical images: a survey. IEEE Trans. on Medical Imaging 22(8), 986–1004 (2003)CrossRefzbMATHGoogle Scholar
  6. 6.
    Ohta, Y., Kanade, T.: Stereo by intra-and inter-scanline search. IEEE Trans. on PAMI 7(2), 139–154 (1985)CrossRefGoogle Scholar
  7. 7.
    Okutomi, M., Kanade, T.: A multiple-baseline stereo. IEEE Trans. on PAMI 15(4), 353–363 (1993)CrossRefGoogle Scholar
  8. 8.
    Tomasi, C., Kanade, T.: Shape and motion from image streams under orthography: a factorization method. IJCV 9(2), 137–154 (1992)CrossRefGoogle Scholar
  9. 9.
    Tomasi, C., Kanade, T.: Detection and tracking of point features. School Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, Tech. Rep. CMU-CS-91–132 (1991)Google Scholar
  10. 10.
    Lowe, D.: Distinctive Image Features from Scale-Invariant Keypoints. IJCV 60(2), 91–110 (2004)CrossRefGoogle Scholar
  11. 11.
    Hashizume, C.: Vinod, V.V., Murase, H.: Robust object extraction from color images under illumination changes. Technical report of IEICE. PRMU 97(325), 33–40 (1997)Google Scholar
  12. 12.
    Pereira, S., Pun, T.: Robust template matching for affine resistant image watermarks. IEEE Trans. on Image Processing 9(6), 1123–1129 (2000)CrossRefGoogle Scholar
  13. 13.
    Uchida, S.: Dp matching: Fundamentals and application. Technical report of IEICE. PRMU, pp. 31–36 (December 2006)Google Scholar
  14. 14.
    Nishimura, T., Oka, R.: Spotting Image Recognition using Two-Dimensional Continuous Dynamic Programming. Technical Report of IEICE. PRMU, 1–7 (July 1997)Google Scholar
  15. 15.
    Myers, C., Rabiner, L., Rosenberg, A.: Performance tradeoffs in dynamic time warping algorithms for isolated word recognition. IEEE Trans. on ASSP 28(6), 623–635 (1980)CrossRefzbMATHGoogle Scholar
  16. 16.
    Uchida, S., Sakoe, H.: Piecewise linear two-dimensional warping. Systems and Computers in Japan 32(12), 1–9 (2001)CrossRefGoogle Scholar
  17. 17.
    Oka, R.: Spotting method for classification of real world data. The Computer Journal 41(8), 559–565 (1998)CrossRefzbMATHGoogle Scholar
  18. 18.
    Yaguchi, Y., Watanabe, Y., Naruse, K., Oka, R.: Speech and Song Search on the Web: System Design and Implementation. In: CIT 2007, pp. 270–278 (2007)Google Scholar
  19. 19.
    Oka, R., Nishimura, T., Yabe, H.: On Spotting Recognition of Gesture Motion from Time-varying Image. Trans. of IPSJ 43, 54–68 (2002)Google Scholar
  20. 20.
    Suto, N., Nishimura, T., Fujii, R.H., Oka, R.: Spotting Recognition of Concave and Convex Reference Image with Pixel-wise Correspondence using Two-dimensional Continuous Dynamic Programming. In: Technical report of IEICE. PRMU (July 2003)Google Scholar
  21. 21.
    Iwasa, Y., Oka, R.: Algorithm for Guaranteeing Monotonuous Contiguity of Pixel Correspondence in Spotting Recognition of Image. In: MIRU 2005, pp. 997–1004 (July 2005)Google Scholar
  22. 22.
    Yaguchi, Y., Iseki, K., Oka, R.: Two-dimensional Continuous Dynamic Programming for Spotting Recognition of Image. In: MIRU 2008, pp. 708–714 (July 2008)Google Scholar
  23. 23.
    Babaguchi, N., Etoh, M., Satoh, S., Adachi, J., Akutsu, A., Ariki, Y., Echigo, T., Shibata, M., Zen, H., Nakamura, Y., Minoh, M.: Video Database for Evaluating Video Processing. In: Technical Report of IEICE. PRMU (June 2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Yuichi Yaguchi
    • 1
  • Kenta Iseki
    • 1
  • Ryuichi Oka
    • 1
  1. 1.The University of AizuFukushimaJapan

Personalised recommendations