Abstract
This paper investigates a convex relaxation approach for minimum description length (MDL) based image partitioning or labeling, which proposes an energy functional regularized by the spatial smoothness prior joint with a penalty for the total number of appearences or labels, the so-called label cost prior. As common in recent studies of convex relaxation approaches, the total-variation term is applied to encode the spatial regularity of partition boundaries and the auxiliary label cost term is penalized by the sum of convex infinity norms of the labeling functions. We study the proposed such convex MDL based image partition model under a novel continuous flow maximization perspective, where we show that the label cost prior amounts to a relaxation of the flow conservation condition which is crucial to study the classical duality of max-flow and min-cut! To the best of our knowledge, it is new to demonstrate such connections between the relaxation of flow conservation and the penalty of the total number of active appearences. In addition, we show that the proposed continuous max-flow formulation also leads to a fast and reliable max-flow based algorithm to address the challenging convex optimization problem, which significantly outperforms the previous approach by direct convex programming, in terms of speed, computation load and handling large-scale images. Its numerical scheme can by easily implemented and accelerated by the advanced computation framework, e.g. GPU.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Ayed, I.B., Mitiche, A.: A region merging prior for variational level set image segmentation. IEEE Trans. Image Processing 17(12), 2301–2311 (2008)
Bae, E., Yuan, J., Tai, X.-C., Boykov, Y.: A fast continuous max-flow approach to non-convex multilabeling problems. Technical report CAM-10-62, UCLA (2010)
Bae, E., Yuan, J., Tai, X.-C.: Global minimization for continuous multiphase partitioning problems using a dual approach. International Journal of Computer Vision 92(1), 112–129 (2011)
Bertsekas, D.P.: Nonlinear Programming. Athena Scientific, Belmont (1999)
Boykov, Y., Kolmogorov, V.: An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. PAMI 26, 359–374 (2001)
Brox, T., Weickert, J.: Level set segmentation with multiple regions. IEEE Transactions on Image Processing 15(10), 3213–3218 (2006)
Chambolle, A., Cremers, D., Pock, T.: A convex approach for computing minimal partitions. Technical Report TR-2008-05, University of Bonn (2008)
Chambolle, A.: An algorithm for total variation minimization and applications. JMIV 20(1), 89–97 (2004)
Delong, A., Osokin, A., Isack, H., Boykov, Y.: Fast approximate energy minimization with label costs. In: CVPR (2010)
Duchi, J., Shalev-Shwartz, S., Singer, Y., Chandra, T.: Efficient projections onto the 1-ball for learning in high dimensions. In: ICML, pp. 272–279 (2008)
Ekeland, I., Téman, R.: Convex analysis and variational problems. Society for Industrial and Applied Mathematics, Philadelphia (1999)
Fan, K.: Minimax theorems. Proc. Nat. Acad. Sci. U.S.A. 39, 42–47 (1953)
Giusti, E.: Minimal surfaces and functions of bounded variation. Australian National University, Canberra (1977)
Gruenwald, P.D.: The Minimum Description Length Principle. MIT Press Books, vol. 1. The MIT Press, Cambridge (2007)
Hiriart-Urruty, J.-B., Lemaréchal, C.: Convex analysis and minimization algorithms I. Springer, Berlin (1993); Fundamentals
Hoiem, D., Rother, C., Winn, J.: 3D LayoutCRF for Multi-View Obect Class Recognition and Segmentation. In: CVPR (2007)
Kadir, T., Brady, M.: Unsupervised non-parametric region segmentation using level sets. In: ICCV, pp. 1267–1274 (2003)
Leclerc, Y.G.: Constructing simple stable descriptions for image partitioning. IJCV 3(1), 73–102 (1989)
Lellmann, J., Kappes, J., Yuan, J., Becker, F., Schnörr, C.: Convex multi-class image labeling by simplex-constrained total variation. Technical report, IWR, Uni. Heidelberg (November 2008)
Li, H.: Two-view motion segmentation from linear programming relaxation. In: CVPR (2007)
Liu, J., Ye, J.: Efficient euclidean projections in linear time. In: International Conference on Machine Learning (2009)
MacKay, D.J.C.: Information Theory, Inference, and Learning Algorithms. Cambridge University Press, Cambridge (2003)
Pock, T., Chambolle, A., Bischof, H., Cremers, D.: A convex relaxation approach for computing minimal partitions. In: CVPR, Miami, Florida (2009)
Vidal, R., Tron, R., Hartley, R.: Multiframe motion segmentation with missing data using powerfactorization and gpca. IJCV 79(1), 85–105 (2008)
Yang, A.Y., Wright, J., Ma, Y., Sastry, S.S.: Unsupervised segmentation of natural images via lossy data compression. Computer Vision and Image Understanding 110(2), 212–225 (2008)
Yuan, J., Bae, E., Tai, X.C.: A study on continuous max-flow and min-cut approaches. In: CVPR, USA, San Francisco (2010)
Yuan, J., Bae, E., Tai, X.-C., Boykov, Y.: A continuous max-flow approach to potts model. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6316, pp. 379–392. Springer, Heidelberg (2010)
Yuan, J., Bae, E., Tai, X.C., Boykov, Y.: A study on continuous max-flow and min-cut approaches. Technical Report CAM 10-61, UCLA (August 2010)
Yuan, J., Boykov, Y.: A continuous max-flow approach to image labelings with label cost prior. In: BMVC (2010)
Zach, C., Gallup, D., Frahm, J.-M., Niethammer, M.: Fast global labeling for real-time stereo using multiple plane sweeps. In: Vision, Modeling and Visualization Workshop, VMV (2008)
Zhu, S.C., Yuille, A.: Region competition: Unifying snakes, region growing, and bayes/mdl for multi-band image segmentation. PAMI 18, 884–900 (1996)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yuan, J., Bae, E., Boykov, Y., Tai, XC. (2012). A Continuous Max-Flow Approach to Minimal Partitions with Label Cost Prior. In: Bruckstein, A.M., ter Haar Romeny, B.M., Bronstein, A.M., Bronstein, M.M. (eds) Scale Space and Variational Methods in Computer Vision. SSVM 2011. Lecture Notes in Computer Science, vol 6667. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24785-9_24
Download citation
DOI: https://doi.org/10.1007/978-3-642-24785-9_24
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24784-2
Online ISBN: 978-3-642-24785-9
eBook Packages: Computer ScienceComputer Science (R0)