Multiple Order Graph Matching
This paper addresses the problem of finding correspondences between two sets of features by using multiple order constraints all together. First, we build a high-order supersymmetric tensor, called multiple order tensor, to incorporate the constraints of different orders (e.g., unary, pairwise, third order, etc.). The multiple order tensor naturally merges multi-granularity geometric affinities, thus it presents stronger descriptive power of consistent constraints than the individual order based methods. Second, to achieve the optimal matching, we present an efficient computational approach for the power iteration of the multiple order tensor. It only needs sparse tensor elements and reduces the sampling size of feature tuples, due to the supersymmetry of the multiple order tensor. The experiments on both synthetic and real image data show that our approach improves the matching performance compared to state-of-the-art algorithms.
Unable to display preview. Download preview PDF.
- 4.Zass, R., Shashua, A.: Probabilistic graph and hypergraph matching. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2008), pp. 1–8 (2008)Google Scholar
- 5.Duchenne, O., Bach, F., Kweon, I., Ponce, J.: A tensor-based algorithm for high-order graph matching. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2009), pp. 1980–1987 (2009)Google Scholar
- 7.Leordeanu, M., Hebert, M.: A spectral technique for correspondence problems using pairwise constraints. In: International Conference of Computer Vision (ICCV 2005), pp. 1482–1489 (2005)Google Scholar
- 10.Cour, T., Srinivasan, P., Shi, J.: Balanced graph matching. In: Advanced in Neural Information Processing Systems (NIPS 2006) (2006)Google Scholar