Abstract
We present an adaptation of the recently proposed graph-shifts algorithm for labeling MRF problems from low-level vision. Graph-shifts is an energy minimization algorithm that does labeling by dynamically manipulating, or shifting, the parent-child relationships in a hierarchical decomposition of the image. Graph-shifts was originally proposed for labeling using relatively small label sets (e.g., 9) for problems in high-level vision. In the low-level vision problems we consider, there are much larger label sets (e.g., 256). However, the original graph-shifts algorithm does not scale well with the number of labels; for example, the memory requirement is quadratic in the number of labels. We propose four improvements to the graph-shifts representation and algorithm that make it suitable for doing labeling on these large label sets. We implement and test the algorithm on two low-level vision problems: image restoration and stereo. Our results demonstrate the potential for such a hierarchical energy minimization algorithm on low-level vision problems with large label sets.
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.
References
Anandan, P.: A Computational Framework and an Algorithm for the Measurement of Visual Motion. International Journal of Computer Vision 2(3), 283–310 (1989)
Besag, J.: Spatial interaction and the statistical analysis of lattice systems (with discussion). J. Royal Stat. Soc., B 36, 192–236 (1974)
Boykov, Y., Veksler, O., Zabih, R.: Fast Approximate Energy Minimization via Graph Cuts. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(11), 1222–1239 (2001)
Corso, J.J., Tu, Z., Yuille, A., Toga, A.W.: Segmentation of Sub-Cortical Structures by the Graph-Shifts Algorithm. In: Karssemeijer, N., Lelieveldt, B. (eds.) Proceedings of Information Processing in Medical Imaging, pp. 183–197 (2007)
Corso, J.J., Yuille, A.L., Sicotte, N.L., Toga, A.W.: Detection and Segmentation of Pathological Structures by the Extended Graph-Shifts Algorithm. In: Ayache, N., Ourselin, S., Maeder, A. (eds.) MICCAI 2007, Part I. LNCS, vol. 4791, pp. 985–994. Springer, Heidelberg (2007)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient Belief Propagation for Early Vision. International Conference on Computer Vision 70(1) (2006)
Freeman, W.T., Pasztor, E.C., Carmichael, O.T.: Learning Low-Level Vision. International Journal of Computer Vision (2000)
Frey, B.J., MacKay, D.: A Revolution: Belief Propagation in Graphs with Cycles. In: Proceedings of Neural Information Processing Systems (NIPS) (1997)
Geman, S., Geman, D.: Stochastic Relaxation, Gibbs Distributions, and Bayesian Restoration of Images. IEEE Transactions on Pattern Analysis and Machine Intelligence 6, 721–741 (1984)
Kolmogorov, V., Zabih, R.: What Energy Functions Can Be Minimized via Graph Cuts? In: European Conference on Computer Vision, vol. 3, pp. 65–81 (2002)
Kumar, S., Hebert, M.: Discriminative Random Fields: A Discriminative Framework for Contextual Interaction in Classification. In: International Conference on Computer Vision (2003)
Lafferty, J., McCallum, A., Pereira, F.: Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. In: Proceedings of International Conference on Machine Learning (2001)
Li, S.Z.: Markov Random Field Modeling in Image Analysis, 2nd edn. Springer, Heidelberg (2001)
Scharstein, D., Szeliski, R.: A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms. International Journal of Computer Vision 47(2), 7–42 (2002)
Szeliski, R., Zabih, R., Scharstein, D., Veksler, O., Kolmogorov, V., Agarwala, A., Tappen, M., Rother, C.: A Comparative Study of Energy Minimization Methods for Markov Random Fields. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part II. LNCS, vol. 3952, pp. 16–29. Springer, Heidelberg (2006)
Wainwright, M.J., Jaakkola, T.S., Willsky, A.S.: Tree-Reweighted Belief Propagation Algorithms and Approximate ML Estimation by Pseudo-Moment Matching. In: AISTATS (2003)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Corso, J.J., Tu, Z., Yuille, A. (2008). MRF Labeling with a Graph-Shifts Algorithm. In: Brimkov, V.E., Barneva, R.P., Hauptman, H.A. (eds) Combinatorial Image Analysis. IWCIA 2008. Lecture Notes in Computer Science, vol 4958. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-78275-9_15
Download citation
DOI: https://doi.org/10.1007/978-3-540-78275-9_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-78274-2
Online ISBN: 978-3-540-78275-9
eBook Packages: Computer ScienceComputer Science (R0)