Abstract
To obtain high-quality segmentation results the integration of semantic information is indispensable. In contrast to existing segmentation methods which use a spatial regularizer, i.e. a local interaction between image points, the co-occurrence prior [15] imposes penalties on the co-existence of different labels in a segmentation. We propose a continuous domain formulation of this prior, using a convex relaxation multi-labeling approach. While the discrete approach [15] is employs minimization by sequential alpha expansions, our continuous convex formulation is solved by efficient primal-dual algorithms, which are highly parallelizable on the GPU. Also, our framework allows isotropic regularizers which do not exhibit grid bias. Experimental results on the MSRC benchmark confirm that the use of co-occurrence priors leads to drastic improvements in segmentation compared to the classical Potts model formulation when applied.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Transactions on Pattern Analysis and Machine Intelligence 23, 2001 (2001)
Chambolle, A., Cremers, D., Pock, T.: A convex approach for computing minimal partitions. Tech. rep. TR-2008-05, University of Bonn (2008)
Chambolle, A., Cremers, D., Pock, T.: A convex approach to minimal partitions. SIAM Journal on Imaging Sciences 5(4), 1113–1158 (2012)
Chambolle, A., Pock, T.: A first-order primal-dual algorithm for convex problems with applications to imaging. JMIV 40(1), 120–145 (2011)
Delong, A., Gorelick, L., Veksler, O., Boykov, Y.: Minimizing energies with hierarchical costs. International Journal of Computer Vision 100(1), 38–58 (2012)
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: Pascal (VOC2010) Results
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. J. Comput. Vision 59(2), 167–181 (2004)
Gilboa, G., Osher, S.: Nonlocal operators with applications to image processing. Multiscale Modeling & Simulation 7(3), 1005–1028 (2008)
Goldluecke, B., Cremers, D.: Convex relaxation for multilabel problems with product label spaces. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 225–238. Springer, Heidelberg (2010)
Goldluecke, B., Strekalovskiy, E., Cremers, D.: Tight convex relaxations for vector-valued labeling. SIAM Journal on Imaging Sciences (2013)
Klodt, M., Schoenemann, T., Kolev, K., Schikora, M., Cremers, D.: An experimental comparison of discrete and continuous shape optimization methods. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 332–345. Springer, Heidelberg (2008)
Kohli, P., Ladicky, L., Torr, P.H.S.: Robust higher order potentials for enforcing label consistency. International Journal of Computer Vision 82(3), 302–324 (2009)
Komodakis, N., Paragios, N., Tziritas, G.: Mrf optimization via dual decomposition: Message-passing revisited. In: IEEE 11th International Conference on Computer Vision, ICCV 2007, pp. 1–8 (2007)
Komodakis, N., Tziritas, G.: Approximate labeling via graph cuts based on linear programming. IEEE Transactions on Pattern Analysis and Machine Intelligence 29(8), 1436–1453 (2007)
Ladický, L., Russell, C., Kohli, P., Torr, P.: Inference methods for crfs with co-occurrence statistics. International Journal of Computer Vision 103(2), 213–225 (2013)
Leclerc, Y.G.: Region growing using the MDL principle. In: Proc. DARPA Image Underst. Workshop, April 6-8, pp. 720–726 (1990)
Lellmann, J., Kappes, J., Yuan, J., Becker, F., Schnörr, C.: Convex multi-class image labeling by simplex-constrained total variation. In: Tai, X.-C., Mørken, K., Lysaker, M., Lie, K.-A. (eds.) SSVM 2009. LNCS, vol. 5567, pp. 150–162. Springer, Heidelberg (2009)
Malik, J., Belongie, S., Leung, T., Shi, J.: Contour and texture analysis for image segmentation. Int. J. Comput. Vision 43(1), 7–27 (2001)
Nieuwenhuis, C., Toeppe, E., Cremers, D.: A survey and comparison of discrete and continuous multilabel segmentation approaches. International Journal of Computer Vision (2013)
Pock, T., Chambolle, A.: Diagonal preconditioning for first order primal-dual algorithms in convex optimization. In: ICCV (2011)
Pock, T., Cremers, D., Bischof, H., Chambolle, A.: An algorithm for minimizing the piecewise smooth mumford-shah functional. In: IEEE International Conference on Computer Vision (ICCV), Kyoto, Japan (2009)
Russell, B.C., Freeman, W.T., Efros, A.A., Sivic, J., Zisserman, A.: Using multiple segmentations to discover objects and their extent in image collections. In: Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006, vol. 2, pp. 1605–1614. IEEE Computer Society, Washington, DC (2006)
Strekalovskiy, E., Goldluecke, B., Cremers, D.: Tight convex relaxations for vector-valued labeling problems. In: ICCV (2011)
Werlberger, M., Unger, M., Pock, T., Bischof, H.: Efficient Minimization of the Non-Local Potts Model. In: ICSSVMCV (2011)
Yuan, J., Boykov, Y.: Tv-based multi-label image segmentation with label cost prior. In: BMVC, pp. 1–12 (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 (October 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
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Souiai, M., Strekalovskiy, E., Nieuwenhuis, C., Cremers, D. (2013). A Co-occurrence Prior for Continuous Multi-label Optimization. In: Heyden, A., Kahl, F., Olsson, C., Oskarsson, M., Tai, XC. (eds) Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 2013. Lecture Notes in Computer Science, vol 8081. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40395-8_16
Download citation
DOI: https://doi.org/10.1007/978-3-642-40395-8_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40394-1
Online ISBN: 978-3-642-40395-8
eBook Packages: Computer ScienceComputer Science (R0)