Feature Correspondence Via Graph Matching: Models and Global Optimization

  • Lorenzo Torresani
  • Vladimir Kolmogorov
  • Carsten Rother
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5303)


In this paper we present a new approach for establishing correspondences between sparse image features related by an unknown non-rigid mapping and corrupted by clutter and occlusion, such as points extracted from a pair of images containing a human figure in distinct poses. We formulate this matching task as an energy minimization problem by defining a complex objective function of the appearance and the spatial arrangement of the features. Optimization of this energy is an instance of graph matching, which is in general a NP-hard problem. We describe a novel graph matching optimization technique, which we refer to as dual decomposition (DD), and demonstrate on a variety of examples that this method outperforms existing graph matching algorithms. In the majority of our examples DD is able to find the global minimum within a minute. The ability to globally optimize the objective allows us to accurately learn the parameters of our matching model from training examples. We show on several matching tasks that our learned model yields results superior to those of state-of-the-art methods.


Global Minimum Uniqueness Constraint Graph Match Feature Correspondence Dual Decomposition 
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.
    Belhumeur, P.N.: A binocular stereo algorithm for reconstructing sloping, creased, and broken surfaces in the presence of half-occlusion. In: ICCV (May 1993)Google Scholar
  2. 2.
    Kolmogorov, V., Zabih, R.: Computing visual correspondence with occlusions using graph cuts. In: ICCV (2001)Google Scholar
  3. 3.
    Dorko, G., Schmid, C.: Selection of scale-invariant parts for object class recognition. In: ICCV (2003)Google Scholar
  4. 4.
    Sivic, J., Russell, B., Efros, A., Zisserman, A.: Discovering object categories in image collections. In: ICCV (2005)Google Scholar
  5. 5.
    Caetano, T.S., Cheng, L., Le, Q.V., Smola, A.J.: Learning graph matching. In: ICCV (2007)Google Scholar
  6. 6.
    Bertsekas, D.: Nonlinear Programming. Athena Scientific (1999)Google Scholar
  7. 7.
    Chardaire, P., Sutter, A.: A decomposition method for quadratic zero-one programming. Management Science 41(4), 704–712 (1995)CrossRefzbMATHGoogle Scholar
  8. 8.
    Wainwright, M.J., Jaakkola, T.S., Willsky, A.S.: MAP estimation via agreement on trees: Message-passing and linear-programming approaches. IEEE Trans. Information Theory 51(11) (2005)Google Scholar
  9. 9.
    Schlesinger, M.I., Giginyak, V.V.: Solution to structural recognition (MAX,+)-problems by their equivalent transformations. Part 1. Control Systems and Computers (1), 3–15 (2007)Google Scholar
  10. 10.
    Schlesinger, M.I., Giginyak, V.V.: Solution to structural recognition (MAX,+)-problems by their equivalent transformations. Part 2. Control Systems and Computers (2), 3–18 (2007)Google Scholar
  11. 11.
    Komodakis, N., Paragios, N., Tziritas, G.: MRF optimization via dual decomposition: Message-passing revisited. In: ICCV (2007)Google Scholar
  12. 12.
    Cour, T., Srinivasan, P., Shi, J.: Balanced graph matching. In: NIPS (2007)Google Scholar
  13. 13.
    Duchi, J., Tarlow, D., Elidan, G., Koller, D.: Using combinatorial optimization within max-product belief propagation. In: NIPS (2007)Google Scholar
  14. 14.
    Belongie, S.J., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. PAMI 24(4), 509–522 (2002)CrossRefGoogle Scholar
  15. 15.
    Torr, P.H.S.: Geometric motion segmentation and model selection. Philosophical Transactions of the Royal Society, 1321–1340 (1998)Google Scholar
  16. 16.
    Sclaroff, S., Pentland, A.: Modal matching for correspondence and recognition. PAMI 17(6), 545–561 (1997)CrossRefGoogle Scholar
  17. 17.
    Berg, A., Berg, T., Malik, J.: Shape matching and object recognition using low distortion correspondence. In: CVPR (2005)Google Scholar
  18. 18.
    Leordeanu, M., Hebert, M.: A spectral technique for correspondence problems using pairwise constraints. In: ICCV (2005)Google Scholar
  19. 19.
    Torr, P.H.S.: Solving Markov random fields using semi definite programming. In: AISTATS (2003)Google Scholar
  20. 20.
    Liu, C.K., Hertzmann, A., Popović, Z.: Learning physics-based motion style with nonlinear inverse optimization. ACM Trans. on Gr. 24(3), 1071–1081 (2005)CrossRefGoogle Scholar
  21. 21.
    Conte, D., Foggia, P., Sansone, C., Vento, M.: Thirty years of graph matching in pattern recognition. Int. J. of Pattern Recognition and Artificial Intelligence 18(3), 265–298Google Scholar
  22. 22.
    Gold, S., Rangarajan, A.: A graduated assignment algorithm for graph matching. PAMI 18(4), 377–388 (1996)CrossRefGoogle Scholar
  23. 23.
    Maciel, J., Costeira, J.: A global solution to sparse correspondence problems. PAMI 25(2), 187–199 (2002)CrossRefGoogle Scholar
  24. 24.
    Cabot, A., Francis, R.: Solving certain nonconvex quadratic minimization problems by ranking the extreme points. Operations Research 18(1), 82–86 (1970)CrossRefzbMATHGoogle Scholar
  25. 25.
    Schellewald, C., Schnörr, C.: Probabilistic subgraph matching based on convex relaxation. In: EMMCVPR (2005)Google Scholar
  26. 26.
    Shor, N.Z.: Minimization methods for nondifferentiable functions. Springer, Heidelberg (1985)CrossRefzbMATHGoogle Scholar
  27. 27.
    Ahuja, R., Magnanti, T., Orlin, J.: Network Flows: Theory, Algorithms, and Applications. Prentice Hall, Englewood Cliffs (1993)zbMATHGoogle Scholar
  28. 28.
    Boros, E., Hammer, P.: Pseudo-boolean optimization. Discr. Appl. Math. 123(1-3) (2002)Google Scholar
  29. 29.
    Hammer, P.L., Hansen, P., Simeone, B.: Roof duality, complementation and persistency in quadratic 0-1 optimization. Mathematicl Programming 28, 121–155 (1984)MathSciNetCrossRefzbMATHGoogle Scholar
  30. 30.
    Torresani, L., Kolmogorov, V., Rother, C.: Feature correspondence via graph matching: Models and global optimization. Technical Report MSR-TR-2008-101 (2008)Google Scholar
  31. 31.
    Boros, E., Hammer, P.L., Sun, X.: Network flows and minimization of quadratic pseudo-Boolean functions. Technical Report RRR 17-1991, RUTCOR (May 1991)Google Scholar
  32. 32.
    Lempitsky, V., Rother, C., Blake, A.: LogCut - efficient graph cut optimization for Markov random fields. In: ICCV (2007)Google Scholar
  33. 33.
    Rother, C., Kolmogorov, V., Lempitsky, V., Szummer, M.: Optimizing binary MRFs via extended roof duality. In: CVPR (2007)Google Scholar
  34. 34.
    Elidan, G., McGraw, I., Koller, D.: Residual belief propagation: Informed scheduling for asynchronous message passing. In: UAI (2006)Google Scholar
  35. 35.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proceedings of the IEEE 86(11), 2278–2324 (1998)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Lorenzo Torresani
    • 1
  • Vladimir Kolmogorov
    • 2
  • Carsten Rother
    • 1
  1. 1.Microsoft Research Ltd.CambridgeUK
  2. 2.University College LondonUK

Personalised recommendations