Subscribe
Issue No.12 - December (2011 vol.33)
pp: 2383-2395
Olivier Duchenne , École Normale Supérieure de Paris and the Willow project team (CNRS/ENS/INRIA UMR 8548)
Francis Bach , INRIA and the Sierra team, Laboratoire d'Informatique de École Normale Supe´rieure de Paris (CNRS/ENS/INRIA UMR 8548)
In-So Kweon , KAIST, Daejeon
Jean Ponce , École Normale Supérieure de Paris and the Willow project team (CNRS/ENS/INRIA UMR 8548)
ABSTRACT
This paper addresses the problem of establishing correspondences between two sets of visual features using higher order constraints instead of the unary or pairwise ones used in classical methods. Concretely, the corresponding hypergraph matching problem is formulated as the maximization of a multilinear objective function over all permutations of the features. This function is defined by a tensor representing the affinity between feature tuples. It is maximized using a generalization of spectral techniques where a relaxed problem is first solved by a multidimensional power method and the solution is then projected onto the closest assignment matrix. The proposed approach has been implemented, and it is compared to state-of-the-art algorithms on both synthetic and real data.
INDEX TERMS
Hypergraphs, graph matching, image feature matching.
CITATION
Olivier Duchenne, Francis Bach, In-So Kweon, Jean Ponce, "A Tensor-Based Algorithm for High-Order Graph Matching", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.33, no. 12, pp. 2383-2395, December 2011, doi:10.1109/TPAMI.2011.110
REFERENCES
 [1] http:/archive3d.net/, 2011. [2] http://vasc.ri.cmu.edu//idb/html/motion/ houseindex.html, 2011. [3] H.A. Almohamad and S.O. Duffuaa, "A Linear Programming Approach for the Weighted Graph Matching Problem," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 5, pp. 522-525, May 1993. [4] D.H. Ballard and C.M. Brown, Computer Vision. Prentice-Hall, 1982. [5] A. Berg, T. Berg, and J. Malik, "Shape Matching and Object Recognition Using Low Distortion Correspondence," Proc. IEEE Conf. Computer Vision Pattern Recognition, vol. 1, pp. 26-33, 2005. [6] S. Birchfield, "KLT: An Implementation of the Kanade-Lucas-Tomasi Feature Tracker," 1998. [7] T. Caetano, L. Cheng, Q.V. Le, and A.J. Smola, "Learning Graph Matching," Proc. IEEE Int'l Conf. Computer Vision, 2007. [8] T. Cour, P. Srinivasan, and J. Shi, "Balanced Graph Matching," Proc. Neural Information Processing Systems, 2007. [9] O. Duchenne, F. Bach, I. Kweon, and J. Ponce, "A Tensor-Based Algorithm for High-Order Graph Matching," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2009. [10] M. Fischler and R. Bolles, "Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography," Comm. ACM, vol. 24, no. 6, pp. 381-395, 1981. [11] G. Frobenius, "Über Matrizen aus Nicht Negativen Elementen," Sitzungsbe-Richte der Koniglich Preussischen Akademie der Wissenschaften, pp. 456-477, 1912. [12] G.H. Golub and C.F. Van Loan, Matrix Computations, third ed. Johns Hopkins Univ. Press, 1996. [13] G. Griffin, A. Holub, and P. Perona, "Caltech-256 Object Category Data Set," Technical Report 7694, California Inst. of Tech nology, 2007. [14] W.E.L. Grimson and T. Lozano-Pérez, "Localizing Overlapping Parts by Searching the Interpretation Tree," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 9, no. 4, pp. 469-482, July 1987. [15] D.P. Huttenlocher and S. Ullman, "Object Recognition Using Alignment," Proc. IEEE Int'l Conf. Computer Vision, 1987. [16] P. Kohli, P. Mudigonda, and P. Torr, "$p^{3}$ and Beyond: Solving Energies with Higher Order Cliques," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2007. [17] L. De Lathauwer, B. De Moor, and J. Vandewalle, "On the Best Rank-1 and Rank-(r1,r2$,\ldots$ ,rn) Approximation of Higher-Order Tensors," SIAM J. Matrix Analysis Applications, vol. 21, no. 4, pp. 1324-1342, 2000. [18] S. Lazebnik, C. Schmid, and J. Ponce, "Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2006. [19] M. Leordeanu and M. Hebert, "A Spectral Technique for Correspondence Problems Using Pairwise Constraints," Proc. IEEE Int'l Conf. Computer Vision, 2005. [20] M. Leordeanu, M. Hebert, and R. Sukthankar, "Beyond Local Appearance: Category Recognition from Pairwise Interactions of Simple Features," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2007. [21] D. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints," Int'l J. Computer Vision, vol. 60, no. 2, pp. 91-110, 2004. [22] D.G. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints," Int'l J. Computer Vision, vol. 60, pp. 91-110, 2004. [23] J. Maciel and J. Costeira, "A Global Solution to Sparse Correspondence Problems," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 25, no. 2, pp. 187-199, Feb. 2003. [24] D.M. Mount and S. Arya, http://www.cs.umd.edu/mountann/ 2011. [25] R. Oliveira, R. Ferreira, and J. Costeira, "Optimal Multi-Frame Correspondence with Assignment Tensors," Proc. European Conf. Computer Vision, 2006. [26] I. Pratikakis, M. Spagnuolo, T. Theoharis, R. Veltkamp, "Shrec09 Track: Generic Shape Retrieval" Proc. EG Workshop 3D Object Retrieval, A. Godil, H. Dutagaci, C. Akgl, A. Axenopoulos, B. Bustos, M. Chaouch, P. Daras, T. Furuya, S. Kreft, Z. Lian, T. Napolon, A. Mademlis, R. Ohbuchi, P.L. Rosin, B. Sankur, T. Schreck, X. Sun, M. Tezuka, A. Verroust-blondet, M. Walter, and Y. Yemez, eds., 2009. [27] P. Pritchett and A. Zisserman, "Wide Baseline Stereo Matching," Proc. IEEE Int'l Conf. Computer Vision, 1998. [28] P.A. Regalia and E. Kofidis, "The Higher-Order Power Method Revisited: Convergence Proofs and Effective Initialization," Proc. IEEE Int'l Conf. Acoustics, Speech, and Signal Processing, 2000. [29] C. Schmid and R. Mohr, "Local Grayvalue Invariants for Image Retrieval," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 5, pp. 530-535, May 1997. [30] S. Umeyama, "An Eigendecomposition Approach to Weighted Graph Matching Problems," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 10, no. 5, pp. 695-703, Sept. 1988. [31] A. Vedaldi, "A Matlab Implementation of Sift," 2008. [32] M. Zaslavskiy, F. Bach, and J.P. Vert, "A Path Following Algorithm for the Graph Matching Problem," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 31, no. 12, pp. 2227-2242, Dec. 2009. [33] R. Zass and A. Shashua, "Probabilistic Graph and Hypergraph Matching," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2008. [34] H. Zhang, A.C. Berg, M. Maire, and J. Malik, "SVM-KNN: Discriminative Nearest Neighbor Classification for Visual Category Recognition," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2006. [35] J. Zhang, M. Marszalek, S. Lazebnik, and C. Schmid, "Local Features and Kernels for Classification of Texture and Object Categories: An In-Depth Study," Int'l J. Computer Vision, vol. 73, no. 2, pp. 213-238, 2007. [36] Y. Zheng and D. Doermann, "Robust Point Matching for Nonrigid Shapes by Preserving Local Neighborhood Structures," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 28, no. 4 pp. 643-649, Apr. 2006.