Embedding Gestalt Laws on Conditional Random Field for Image Segmentation

  • Olfa Besbes
  • Nozha Boujemaa
  • Ziad Belhadj
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6938)

Abstract

We propose a higher order conditional random field built over a graph of superpixels for partitioning natural images into coherent segments. Our model operates at both superpixel and segment levels and includes potentials that capture similarity, proximity, curvilinear continuity and familiar configuration. For a given image, these potentials enforce consistency and regularity of labellings. The optimal one should maximally satisfy local, pairwise and global constraints imposed respectively by the learned association, interaction and higher order potentials. Experiments on a variety of natural images show that integration of higher order potentials qualitatively and quantitatively improves results and leads to more coherent and regular segments.

Keywords

Image Segmentation Pattern Anal Natural Image High Order Potential Proposal Probability 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Zhu, S.C., Yuille, A.: Region competition: Unifying snakes, region growing, and bayes/mdl for multiband image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 18, 884–900 (1996)CrossRefGoogle Scholar
  2. 2.
    Chen, Y., Tagare, H., Thiruvenkadam, S., Huang, F., Wilson, D., Gopinath, K., Briggs, R., Geiser, E.: Using prior shapes in geometric active contours in a variational framework. Int. J. Comput. Vision 50, 315–328 (2002)CrossRefMATHGoogle Scholar
  3. 3.
    Kato, Z., Pong, T.C., Lee, J.C.M.: Color image segmentation and parameter estimation in a markovian framework. Pattern Recogn. Lett. 22, 309–321 (2001)CrossRefMATHGoogle Scholar
  4. 4.
    Bertelli, L., Sumengen, B., Manjunath, B., Gibou, F.: A variational framework for multiregion pairwise-similarity-based image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 30, 1400–1414 (2008)CrossRefGoogle Scholar
  5. 5.
    Cremers, D., Rousson, M., Deriche, R.: A review of statistical approaches to level set segmentation: integrating color, texture, motion and shape. Int. J. Comput. Vision 72, 195–215 (2007)CrossRefGoogle Scholar
  6. 6.
    Tu, Z., Zhu, S.C.: Image segmentation by data-driven markov chain monte carlo. IEEE Trans. Pattern Anal. Mach. Intell. 24, 657–673 (2002)CrossRefGoogle Scholar
  7. 7.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell. 23, 1222–1239 (2001)CrossRefGoogle Scholar
  8. 8.
    Barbu, A., Zhu, S.C.: Generalizing swendsen-wang to sampling arbitrary posterior probabilities. IEEE Trans. Pattern Anal. Mach. Intell. 27, 1239–1253 (2005)CrossRefGoogle Scholar
  9. 9.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 22, 888–905 (2000)CrossRefGoogle Scholar
  10. 10.
    Kim, T.H., Lee, K.M., Lee, S.U.: Learning full pairwise affinities for spectral segmentation. In: IEEE CVPR, pp. 2101–2108 (2010)Google Scholar
  11. 11.
    Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: ICML, vol. 18, pp. 282–289 (2001)Google Scholar
  12. 12.
    Kumar, S., Hebert, M.: Discriminative random fields. Int. J. Comput. Vision 68(2), 179–201 (2006)CrossRefGoogle Scholar
  13. 13.
    Ren, X., Fowlkes, C.C., Malik, J.: Figure/ground assignment in natural images. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part I. LNCS, vol. 3952, pp. 614–627. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  14. 14.
    He, X., Zemel, R.S., Carreira-Perpinan, M.A.: Multiscale conditional random fields for image labeling (2004)Google Scholar
  15. 15.
    He, X., Zemel, R.S., Ray, D.: Learning and incorporating top-down cues in image segmentation. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part I. LNCS, vol. 3951, pp. 338–351. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  16. 16.
    Shotton, J., Winn, J.M., Rother, C., Criminisi, A.: Textonboost for image understanding: Multi-class object recognition and segmentation by jointly modeling texture, layout, and context. Int. J. Comput. Vision 81, 2–23 (2009)CrossRefGoogle Scholar
  17. 17.
    Ren, X., Fowlkes, C., Malik, J.: Learning probabilistic models for contour completion in natural images. Int. J. Comput. Vision 77, 47–63 (2008)CrossRefGoogle Scholar
  18. 18.
    Ren, X., Malik, J.: Learning a classification model for segmentation. In: IEEE ICCV, vol. 2, pp. 10–18 (2003)Google Scholar
  19. 19.
    Kohli, P., Ladicky, L.U., Torr, P.H.: Robust higher order potentials for enforcing label consistency. Int. J. Comput. Vision 82, 302–324 (2009)CrossRefGoogle Scholar
  20. 20.
    Brox, T., Weickert, J.: A tv flow based local scale estimate and its application to texture discrimination. J. of Visual Communication and Image Representation 17, 1053–1073 (2006)CrossRefGoogle Scholar
  21. 21.
    Martin, D., Fowlkes, C., Malik, J.: Learning to detect natural image boundaries using local brightness, color and texture cues. IEEE Trans. Pattern Anal. Mach. Intell. 26, 530–549 (2004)CrossRefGoogle Scholar
  22. 22.
    Torralba, A., Murphy, K.P., Freeman, W.T.: Sharing visual features for multiclass and multiview object detection. IEEE Trans. Pattern Anal. Mach. Intell. 29, 854–869 (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Olfa Besbes
    • 1
  • Nozha Boujemaa
    • 2
  • Ziad Belhadj
    • 1
  1. 1.URISA - SUPCOM, Parc TechnologiqueArianaTunisia
  2. 2.INRIA Saclay Île-de-FranceOrsayFrance

Personalised recommendations