Pixel-to-Pixel Matching for Image Recognition Using Hungarian Graph Matching

  • Daniel Keysers
  • Thomas Deselaers
  • Hermann Ney
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3175)


A fundamental problem in image recognition is to evaluate the similarity of two images. This can be done by searching for the best pixel-to-pixel matching taking into account suitable constraints. In this paper, we present an extension of a zero-order matching model called the image distortion model that yields state-of-the-art classification results for different tasks. We include the constraint that in the matching process each pixel of both compared images must be matched at least once. The optimal matching under this constraint can be determined using the Hungarian algorithm. The additional constraint leads to more homogeneous displacement fields in the matching. The method reduces the error rate of a nearest neighbor classifier on the well known USPS handwritten digit recognition task from 2.4% to 2.2%.


Bipartite Graph Minimum Weight Image Recognition Image Match Graph Match 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Belongie, S., Malik, J., Puzicha, J.: Shape Matching and Object Recognition Using Shape Contexts. IEEE Trans. Pattern Analysis and Machine Intelligence 24(4), 509–522 (2002)CrossRefGoogle Scholar
  2. 2.
    Dong, J.X., Krzyzak, A., Suen, C.Y.: A Practical SMO Algorithm. In: Proc. Int. Conf. on Pattern Recognition, Quebec City, Canada (August 2002)Google Scholar
  3. 3.
    Keijsper, J., Pendavingh, R.: An Efficient Algorithm for Minimum-Weight Bibranching. Technical Report 96-12, Amsterdam Univ., Amsterdam, The Netherlands (1996)Google Scholar
  4. 4.
    Keysers, D., Paredes, R., Ney, H., Vidal, E.: Combination of Tangent Vectors and Local Representations for Handwritten Digit Recognition. In: Caelli, T.M., Amin, A., Duin, R.P.W., Kamel, M.S., de Ridder, D. (eds.) SPR 2002 and SSPR 2002. LNCS, vol. 2396, pp. 538–547. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  5. 5.
    Keysers, D., Gollan, C., Ney, H.: Classification of Medical Images using Non-linear Distortion Models. In: Proc. BVM 2004, Bildverarbeitung für die Medizin, Berlin, Germany, March 2004, pp. 366–370 (2004)Google Scholar
  6. 6.
    Keysers, D., Gollan, C., Ney, H.: Local Context in Non-linear Deformation Models for Handwritten Character Recognition. In: ICPR 2004, 17th Int. Conf. on Pattern Recognition, Cambridge, UK (August 2004) (in press)Google Scholar
  7. 7.
    Knuth, D.E.: The Stanford GraphBase: A Platform for Combinatorial Computing. Addison-Wesley, Reading (1994)zbMATHGoogle Scholar
  8. 8.
    Schölkopf, B., Simard, P., Smola, A., Vapnik, V.: Prior Knowledge in Support Vector Kernels. In: Advances in Neural Information Processing Systems 10, pp. 640–646. MIT Press, Cambridge (1998)Google Scholar
  9. 9.
    Wiskott, L., Fellous, J., Krüger, N., Malsburg, C.v.d.: Face Recognition by Elastic Bunch Graph Matching. IEEE Trans. Pattern Analysis and Machine Intelligence 19(7), 775–779 (1997)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Daniel Keysers
    • 1
  • Thomas Deselaers
    • 1
  • Hermann Ney
    • 1
  1. 1.Lehrstuhl für Informatik VI, Computer Science DepartmentRWTH Aachen UniversityAachenGermany

Personalised recommendations