Abstract

Image partitioning separates an image into multiple visually and semantically homogeneous regions, providing a summary of visual content. Knowing that human observers focus on interesting objects or regions when interpreting a scene, and envisioning the usefulness of this focus in many computer vision tasks, this paper develops a user-attention adaptive image partitioning approach. Given a set of pairs of oversegments labeled by a user as ”should be merged” or ”should not be merged”, the proposed approach produces a fine partitioning in user defined interesting areas, to retain interesting information, and a coarser partitioning in other regions to provide a parsimonious representation. To achieve this, a novel Markov Random Field (MRF) model is used to optimally infer the relationship (”merge” or ”not merge”) among oversegment pairs, by using the graph nodes to describe the relationship between pairs. By training an SVM classifier to provide the data term, a graph-cut algorithm is employed to infer the best MRF configuration. We discuss the difficulty in translating this configuration back to an image labelling, and develop a non-trivial post-processing to refine the configuration further. Experimental verification on benchmark data sets demonstrates the effectiveness of the proposed approach.

References

  1. 1.
    Weichselgartner, E., Sperling, G.: Dynamics of automatic and controlled visual attention. Science 238, 778–780 (1987)CrossRefGoogle Scholar
  2. 2.
    Felzenszwalb, P., Huttenlocher, D.: Efficient graph-based image segmentation. Int. J. Comput. Vision 59(2), 167–181 (2004)CrossRefGoogle Scholar
  3. 3.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 22, 888–905 (2000)CrossRefGoogle Scholar
  4. 4.
    Nock, R., Nielsen, F.: Semi-supervised statistical region refinement for color image segmentation 38(6), 835–846 (2005)Google Scholar
  5. 5.
    Mori, G.: Guiding model search using segmentation. In: ICCV 2005, vol. 2, pp. 1417–1423 (October 2005)Google Scholar
  6. 6.
    Moore, A., Prince, S., Warrell, J., Mohammed, U., Jones, G.: Superpixel lattices. In: CVPR 2008, June 2008, pp. 1–8 (2008)Google Scholar
  7. 7.
    Meyer, F., Beucher, S.: Morphological segmentation 1(1), 21–46 (September 1990)Google Scholar
  8. 8.
    Varma, M., Zisserman, A.: Classifying images of materials: Achieving viewpoint and illumination independence. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 255–271. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  9. 9.
    Li, S.Z.: Markov random field modeling in image analysis. Springer, New York (2001)MATHGoogle Scholar
  10. 10.
    Rosvall, M., Trusina, A., Minnhagen, P., Sneppen, K.: Networks and cities: An information perspective. Physical Review Letters 94 (January 2005)Google Scholar
  11. 11.
    Boykov, Y., Kolmogorov, V.: An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE Trans. Pattern Anal. Mach. Intell. 26(9), 1124–1137 (2004)CrossRefGoogle Scholar
  12. 12.
    Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines (2001) Software available at, http://www.csie.ntu.edu.tw/~cjlin/libsvm
  13. 13.
    Shotton, J., Winn, J., Rother, C., Criminisi, A.: Textonboost: Joint appearance, shape and context modeling for multi-class object recognition and segmentation. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 1–15. Springer, Heidelberg (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Nathan Brewer
    • 1
    • 2
  • Nianjun Liu
    • 2
  • Lei Wang
    • 1
  1. 1.College of Engineering and Computer ScienceAustralian National UniversityCanberraAustralia
  2. 2.Canberra Research LaboratoryNICTACanberraAustralia

Personalised recommendations