Abstract
The two-class clustering problem is formulated as an integer convex optimisation problem which determines the maximum of the Earth Movers Distance (EMD) between two classes, constructing a bipartite graph with minimum flow and maximum inter-class EMD between two sets. Subsequently including the nearest neighbours of the start point in feature space and calculating the EMD for this labellings quickly converges to a robust optimum. A histogram of grey values with the number of bins b as the only parameter is used as feature, which makes run time complexity independent of the number of pixels. After convergence in \(\mathcal{O}(b)\) steps, spatial correlations can be taken into account by total variational smoothing. Testing the algorithm on real world images from commonly used databases reveals that it is competitive to state-of-the-art methods, while it deterministically yields hard assignments without requiring any a priori knowledge of the input data or similarity matrices to be calculated.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Vaserstein, L.N.: On the stabilization of the general linear group over a ring. Math. USSR-Sbornik 8, 383–400 (1969)
Peleg, S., Werman, M., Rom, H.: A unified approach to the change of resolution: Space and gray-level. IEEE Trans. Pattern Anal. Mach. Intell. 11, 739–742 (1989)
Rubner, Y., Tomasi, C., Guibas, L.J.: The earth mover’s distance as a metric for image retrieval. Int. J. Comput. Vision 40, 99–121 (2000)
Ling, H., Okada, K.: An efficient earth mover’s distance algorithm for robust histogram comparison. IEEE Trans. Pat. Anal. Mach. Intell. 29, 840–853 (2007)
Pavan, M., Pelillo, M.: Dominant sets and pairwise clustering. IEEE Trans. Patt. Anal. Mach. Intell. 29, 167–172 (2007)
Cour, T., Benezit, F., Shi, J.: Spectral segmentation with multiscale graph decomposition. In: CVPR 2005: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Washington, DC, vol. 2, pp. 1124–1131. IEEE Computer Society, Los Alamitos (2005)
Xu, L., Neufeld, J., Larson, B., Schuurmans, D.: Maximum margin clustering. In: Saul, L.K., Weiss, Y., Bottou, L. (eds.) Advances in Neural Information Processing Systems 17, pp. 1537–1544. MIT Press, Cambridge (2005)
Gieseke, F., Pahikkala, T., Kramer, O.: Fast evolutionary maximum margin clustering. In: ICML 2009: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 361–368. ACM, New York (2009)
Zass, R., Shashua, A.: A unifying approach to hard and probabilistic clustering. In: Proc. ICCV, vol. 1, pp. 294–301 (2005)
Nesterov, Y.: Smooth minimization of non-smooth functions. Math. Program. 103, 127–152 (2005)
Rother, C., Kolmogorov, V., Blake, A.: “grabcut”: interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. 23, 309–314 (2004)
Sommer, C., Straehle, C., Köthe, U., Hamprecht, F.: Interactive learning and segmentation tool kit 0.8, rev 475 (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wagner, J., Ommer, B. (2011). Efficient Clustering Earth Mover’s Distance. In: Kimmel, R., Klette, R., Sugimoto, A. (eds) Computer Vision – ACCV 2010. ACCV 2010. Lecture Notes in Computer Science, vol 6493. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19309-5_37
Download citation
DOI: https://doi.org/10.1007/978-3-642-19309-5_37
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-19308-8
Online ISBN: 978-3-642-19309-5
eBook Packages: Computer ScienceComputer Science (R0)