Abstract
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.
Chapter PDF
Similar content being viewed by others
Keywords
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
Belhumeur, P.N.: A binocular stereo algorithm for reconstructing sloping, creased, and broken surfaces in the presence of half-occlusion. In: ICCV (May 1993)
Kolmogorov, V., Zabih, R.: Computing visual correspondence with occlusions using graph cuts. In: ICCV (2001)
Dorko, G., Schmid, C.: Selection of scale-invariant parts for object class recognition. In: ICCV (2003)
Sivic, J., Russell, B., Efros, A., Zisserman, A.: Discovering object categories in image collections. In: ICCV (2005)
Caetano, T.S., Cheng, L., Le, Q.V., Smola, A.J.: Learning graph matching. In: ICCV (2007)
Bertsekas, D.: Nonlinear Programming. Athena Scientific (1999)
Chardaire, P., Sutter, A.: A decomposition method for quadratic zero-one programming. Management Science 41(4), 704–712 (1995)
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)
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)
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)
Komodakis, N., Paragios, N., Tziritas, G.: MRF optimization via dual decomposition: Message-passing revisited. In: ICCV (2007)
Cour, T., Srinivasan, P., Shi, J.: Balanced graph matching. In: NIPS (2007)
Duchi, J., Tarlow, D., Elidan, G., Koller, D.: Using combinatorial optimization within max-product belief propagation. In: NIPS (2007)
Belongie, S.J., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. PAMI 24(4), 509–522 (2002)
Torr, P.H.S.: Geometric motion segmentation and model selection. Philosophical Transactions of the Royal Society, 1321–1340 (1998)
Sclaroff, S., Pentland, A.: Modal matching for correspondence and recognition. PAMI 17(6), 545–561 (1997)
Berg, A., Berg, T., Malik, J.: Shape matching and object recognition using low distortion correspondence. In: CVPR (2005)
Leordeanu, M., Hebert, M.: A spectral technique for correspondence problems using pairwise constraints. In: ICCV (2005)
Torr, P.H.S.: Solving Markov random fields using semi definite programming. In: AISTATS (2003)
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)
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), 265–298
Gold, S., Rangarajan, A.: A graduated assignment algorithm for graph matching. PAMI 18(4), 377–388 (1996)
Maciel, J., Costeira, J.: A global solution to sparse correspondence problems. PAMI 25(2), 187–199 (2002)
Cabot, A., Francis, R.: Solving certain nonconvex quadratic minimization problems by ranking the extreme points. Operations Research 18(1), 82–86 (1970)
Schellewald, C., Schnörr, C.: Probabilistic subgraph matching based on convex relaxation. In: EMMCVPR (2005)
Shor, N.Z.: Minimization methods for nondifferentiable functions. Springer, Heidelberg (1985)
Ahuja, R., Magnanti, T., Orlin, J.: Network Flows: Theory, Algorithms, and Applications. Prentice Hall, Englewood Cliffs (1993)
Boros, E., Hammer, P.: Pseudo-boolean optimization. Discr. Appl. Math. 123(1-3) (2002)
Hammer, P.L., Hansen, P., Simeone, B.: Roof duality, complementation and persistency in quadratic 0-1 optimization. Mathematicl Programming 28, 121–155 (1984)
Torresani, L., Kolmogorov, V., Rother, C.: Feature correspondence via graph matching: Models and global optimization. Technical Report MSR-TR-2008-101 (2008)
Boros, E., Hammer, P.L., Sun, X.: Network flows and minimization of quadratic pseudo-Boolean functions. Technical Report RRR 17-1991, RUTCOR (May 1991)
Lempitsky, V., Rother, C., Blake, A.: LogCut - efficient graph cut optimization for Markov random fields. In: ICCV (2007)
Rother, C., Kolmogorov, V., Lempitsky, V., Szummer, M.: Optimizing binary MRFs via extended roof duality. In: CVPR (2007)
Elidan, G., McGraw, I., Koller, D.: Residual belief propagation: Informed scheduling for asynchronous message passing. In: UAI (2006)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proceedings of the IEEE 86(11), 2278–2324 (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Torresani, L., Kolmogorov, V., Rother, C. (2008). Feature Correspondence Via Graph Matching: Models and Global Optimization. In: Forsyth, D., Torr, P., Zisserman, A. (eds) Computer Vision – ECCV 2008. ECCV 2008. Lecture Notes in Computer Science, vol 5303. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-88688-4_44
Download citation
DOI: https://doi.org/10.1007/978-3-540-88688-4_44
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-88685-3
Online ISBN: 978-3-540-88688-4
eBook Packages: Computer ScienceComputer Science (R0)