Advertisement

Abstract

We propose a combination of shape prior models with Markov Random Fields. The model allows to integrate multiple shape priors and appearance models into MRF-models for segmentation. We discuss a recognition task and introduce a general learning scheme. Both tasks are solved in the scope of the model and verified experimentally.

Keywords

Appearance Model Conditional Random Field Markov Random Statistical Shape Model Shape Prior 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Greig, D.M., Porteous, B.T., Scheult, A.H.: Exact maximum a posteriori estimation for binary images. Journal of the Royal Statistical Society B 51(2), 271–279 (1989)Google Scholar
  2. 2.
    Kolmogorov, V., Zabih, R.: What energy functions can be minimized via graph cuts? In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 65–81. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  3. 3.
    Schlesinger, D., Flach, B.: Transforming an arbitrary minsum problem into a binary one. Technical Report TUD-FI06-01, Dresden University of Technology (April 2006)Google Scholar
  4. 4.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. In: Proc. of the 7. Intl. Conf. on Computer Vision, vol. 1, pp. 377–384 (1999)Google Scholar
  5. 5.
    Kovtun, I.: Partial optimal labeling search for a NP-hard subclass of (max,+) problems. In: Michaelis, B., Krell, G. (eds.) DAGM 2003. LNCS, vol. 2781, pp. 402–409. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  6. 6.
    Kolmogorov, V.: Convergent tree-reweighted message passing for energy minimization. IEEE Transactions on Pattern Analysis and Machine Intelligence 28(10), 1568–1583 (2006)CrossRefGoogle Scholar
  7. 7.
    Leventon, M.E., Grimson, W.E., Faugeras, O.: Statistical shape influence in geodesic active contours. In: Proc. IEEE Conf. Comp. Vision and Patt. Recog. (2000)Google Scholar
  8. 8.
    Cremers, D., Sochen, N., Schnörr, C.: A multiphase dynamic labeling model for variational recognition-driven image segmentation. International Journal of Computer Vision 66(1), 67–81 (2006)CrossRefzbMATHGoogle Scholar
  9. 9.
    Pohl, K.M., et al.: Shape based segmentation of anatomical structures in magnetic resonance images. In: Liu, Y., Jiang, T., Zhang, C. (eds.) CVBIA 2005. LNCS, vol. 3765, pp. 489–498. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  10. 10.
    Kumar, M.P., Torr, P.H.S., Zisserman, A.: An object category specific MRF for segmentation. In: Ponce, J., Hebert, M., Schmid, C., Zisserman, A. (eds.) Toward Category-Level Object Recognition. LNCS, vol. 4170, pp. 596–616. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  11. 11.
    Levin, A., Weiss, Y.: Learning to combine bottom-up and top-down segmentation. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3954, pp. 581–594. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  12. 12.
    Verbeek, J., Triggs, B.: Scene segmentation with CRFs learned from partially labeled images. In: Advances in Neural Information Processing Systems, vol. 20 (2008)Google Scholar
  13. 13.
    Schlesinger, D., Flach, B.: A probabilistic segmentation scheme. In: Rigoll, G. (ed.) DAGM 2008. LNCS, vol. 5096, pp. 183–192. Springer, Heidelberg (2008)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Boris Flach
    • 1
  • Dmitrij Schlesinger
    • 1
  1. 1.Dresden University of TechnologyGermany

Personalised recommendations