Many-to-Many Feature Matching Using Spherical Coding of Directed Graphs
Abstract
In recent work, we presented a framework for many-to-many matching of multi-scale feature hierarchies, in which features and their relations were captured in a vertex-labeled, edge-weighted directed graph. The algorithm was based on a metric-tree representation of labeled graphs and their metric embedding into normed vector spaces, using the embedding algorithm of Matousek [13]. However, the method was limited by the fact that two graphs to be matched were typically embedded into vector spaces with different dimensionality. Before the embeddings could be matched, a dimensionality reduction technique (PCA) was required, which was both costly and prone to error. In this paper, we introduce a more efficient embedding procedure based on a spherical coding of directed graphs. The advantage of this novel embedding technique is that it prescribes a single vector space into which both graphs are embedded. This reduces the problem of directed graph matching to the problem of geometric point matching, for which efficient many-to-many matching algorithms exist, such as the Earth Mover’s Distance. We apply the approach to the problem of multi-scale, view-based object recognition, in which an image is decomposed into a set of blobs and ridges with automatic scale selection.
Keywords
Feature Match Graph Match Normed Vector Space Graph Edit Distance Spherical CodeReferences
- 1.Agarwala, R., Bafna, V., Farach, M., Paterson, M., Thorup, M.: On the approximability of numerical taxonomy (fitting distances by tree metrics). SIAM Journal on Computing 28(2), 1073–1085 (1999)zbMATHMathSciNetGoogle Scholar
- 2.Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE PAMI 24(4), 509–522 (2002)Google Scholar
- 3.Beveridge, R., Riseman, E.M.: How easy is matching 2D line models using local search? IEEE Transactions on Pattern Analysis and Machine Intelligence 19(6), 564–579 (1997)CrossRefGoogle Scholar
- 4.Buneman, P.: The recovery of trees from measures of dissimilarity. In: Hodson, F., Kendall, D., Tautu, P. (eds.) Mathematics in the Archaeological and Historical Sciences, pp. 387–395. Edinburgh University Press, Edinburgh (1971)Google Scholar
- 5.Cohen, S.D., Guibas, L.J.: The earth mover’s distance under transformation sets. In: Proceedings of 7th International Conference on Computer Vision, Kerkyra, Greece, pp. 1076–1083 (1999)Google Scholar
- 6.Conway, J.H., Sloane, N.J.A.: Sphere Packing, Lattices and Groups. Springer, New York (1998)Google Scholar
- 7.Demirci, F., Shokoufandeh, A., Keselman, Y., Dickinson, S., Bretzner, L.: Manyto- many matching of scale-space feature hierarchies using metric embedding. In: 4th International Conference on Scale Space Methods in Computer Vision, Isle of Skye, UK, June, 10–12, pp. 17–32 (2003)Google Scholar
- 8.Gupta, A.: Embedding tree metrics into low dimensional euclidean spaces. In: Proceedings of the thirty-first annual ACM symposium on Theory of computing, pp. 694–700 (1999)Google Scholar
- 9.Indyk, P.: Algorithmic aspects of geometric embeddings. In: Proceedings of 42nd Annual Symposium on Foundations of Computer Science (2001)Google Scholar
- 10.Keselman, Y., Shokoufandeh, A., Demirci, F., Dickinson, S.: Many-to-many graph matching via low-distortion embedding. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Madison, WI (June 2003)Google Scholar
- 11.Kosinov, S., Caelli, T.: Inexact multisubgraph matching using graph eigenspace and clustering models. 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. 133–142. Springer, Heidelberg (2002)CrossRefGoogle Scholar
- 12.Liu, T.-L., Geiger, D.: Approximate tree matching and shape similarity. In: Proceedings of 7th International Conference on Computer Vision, Kerkyra, Greece, pp. 456–462 (1999)Google Scholar
- 13.Matoušek, J.: On embedding trees into uniformly convex Banach spaces. Israel Journal of Mathematics 237, 221–237 (1999)CrossRefGoogle Scholar
- 14.Messmer, B., Bunke, H.: Efficient error-tolerant subgraph isomorphism detection. In: Dori, D., Bruckstein, A. (eds.) Shape, Structure and Pattern Recognition, pp. 231–240. World Scientific Publ. Co., Singapore (1995)Google Scholar
- 15.Myers, R., Wilson, R., Hancock, E.: Bayesian graph edit distance. IEEE PAMI 22(6), 628–635 (2000)Google Scholar
- 16.Rubner, Y., Tomasi, C., Guibas, L.J.: The earth mover’s distance as a metric for image retrieval. International Journal of Computer Vision 40(2), 99–121 (2000)zbMATHCrossRefGoogle Scholar
- 17.Scott, G., Longuet-Higgins, H.: An algorithm for associating the features of two patterns. Proceedings of Royal Society of London B244, 21–26 (1991)CrossRefGoogle Scholar
- 18.Sebastian, T., Klein, P., Kimia, B.: Recognition of shapes by editing shock graphs. In: IEEE International Conference on Computer Vision, pp. 755–762 (2001)Google Scholar
- 19.Shokoufandeh, A., Dickinson, S.J., Jönsson, C., Bretzner, L., Lindeberg, T.: On the representation and matching of qualitative shape at multiple scales. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 759–775. Springer, Heidelberg (2002)CrossRefGoogle Scholar
- 20.Siddiqi, K., Shokoufandeh, A., Dickinson, S., Zucker, S.: Shock graphs and shape matching. International Journal of Computer Vision 30, 1–24 (1999)Google Scholar