Image Segmentation with Topic Random Field

  • Bin Zhao
  • Li Fei-Fei
  • Eric P. Xing
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6315)

Abstract

Recently, there has been increasing interests in applying aspect models (e.g., PLSA and LDA) in image segmentation. However, these models ignore spatial relationships among local topic labels in an image and suffers from information loss by representing image feature using the index of its closest match in the codebook. In this paper, we propose Topic Random Field (TRF) to tackle these two problems. Specifically, TRF defines a Markov Random Field over hidden labels of an image, to enforce the spatial coherence between topic labels for neighboring regions. Moreover, TRF utilizes a noise channel to model the generation of local image features, and avoids the off-line process of building visual codebook. We provide details of variational inference and parameter learning for TRF. Experimental evaluations on three image data sets show that TRF achieves better segmentation performance.

Keywords

Image Segmentation Visual Word Segmentation Result Markov Random Field Latent Dirichlet Allocation 
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.

Supplementary material

978-3-642-15555-0_57_MOESM1_ESM.pdf (86 kb)
Electronic Supplementary Material (86 KB)

References

  1. 1.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 22, 888–905 (2000)CrossRefGoogle Scholar
  2. 2.
    Comaniciu, D., Meer, P.: Mean shift: A robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell. 24, 603–619 (2002)CrossRefGoogle Scholar
  3. 3.
    Felzenszwalb, P., Huttenlocher, D.: Efficient graph-based image segmentation. International Journal of Computer Vision 59, 167–181 (2004)CrossRefGoogle Scholar
  4. 4.
    Forsyth, D., Ponce, J.: Computer Vision: A Modern Approach. Prentice Hall Professional Technical Reference (2002)Google Scholar
  5. 5.
    Hofmann, T.: Unsupervised learning by probabilistic latent semantic analysis. Mach. Learn. 42, 177–196 (2001)MATHCrossRefGoogle Scholar
  6. 6.
    Blei, D., Ng, A., Jordan, M.: Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003)MATHCrossRefGoogle Scholar
  7. 7.
    Fei-Fei, L., Perona, P.: A bayesian hierarchical model for learning natural scene categories. In: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 524–531 (2005)Google Scholar
  8. 8.
    Fergus, R., Fei-Fei, L., Perona, P., Zisserman, A.: Learning object categories from google”s image search. In: Proceedings of the Tenth IEEE International Conference on Computer Vision, pp. 1816–1823 (2005)Google Scholar
  9. 9.
    Russell, B., Freeman, W., Efros, 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, pp. 1605–1614 (2006)Google Scholar
  10. 10.
    Sivic, J., Russell, B., Efros, A., Zisserman, A., Freeman, W.: Discovering object categories in image collections. In: Proceedings of the Tenth International Conference on Computer Vision (2005)Google Scholar
  11. 11.
    Verbeek, J., Triggs, B.: Region classification with markov field aspect models. In: Proceedings of the 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2007)Google Scholar
  12. 12.
    Li, L.J., Socher, R., Fei-Fei, L.: Towards total scene understanding:classification, annotation and segmentation in an automatic framework. In: Proceedings of the 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2009)Google Scholar
  13. 13.
    Cao, L., Fei-Fei, L.: Spatially coherent latent topic model for concurrent object segmentation and classification. In: Proceedings of IEEE International Conference on Computer Vision (2007)Google Scholar
  14. 14.
    Kadir, T., Brady, M.: Saliency, scale and image description. Int. J. Comput. Vision 45, 83–105 (2001)MATHCrossRefGoogle Scholar
  15. 15.
    Sudderth, E., Jordan, M.: Shared segmentation of natural scenes using dependent pitman-yor processes. In: Proceedings of Neural Information Processing Systems (2008)Google Scholar
  16. 16.
    Andreetto, M., Zelnik-Manor, L., Perona, P.: Unsupervised learning of categorical segments in image collections. In: Proceedings of IEEE International Conference on Computer Vision (2008)Google Scholar
  17. 17.
    Levin, A., Weiss, Y.: Learning to combine bottom-up and top-down segmentation. Int. J. Comput. Vision 81, 105–118 (2009)CrossRefGoogle Scholar
  18. 18.
    Malisiewicz, T., Efros, A.: Recognition by association via learning per-exemplar distances. In: Proceedings of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2008)Google Scholar
  19. 19.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60, 91–110 (2004)CrossRefGoogle Scholar
  20. 20.
    Schwarz, G.: Estimating the dimension of a model. The annals of statistics 6, 461–464 (1978)MATHCrossRefMathSciNetGoogle Scholar
  21. 21.
    Wainwright, M., Jordan, M.: Graphical Models, Exponential Families, and Variational Inference. Now Publishers Inc. (2008)Google Scholar
  22. 22.
    Borenstein, E., Ullman, S.: Learning to segment. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3023, pp. 315–328. Springer, Heidelberg (2004)Google Scholar
  23. 23.
    Winn, J., Criminisi, A., Minka, T.: Object categorization by learned universal visual dictionary. In: Proceedings of IEEE International Conference on Computer Vision (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Bin Zhao
    • 1
  • Li Fei-Fei
    • 2
  • Eric P. Xing
    • 1
  1. 1.School of Computer ScienceCarnegie Mellon University 
  2. 2.Computer Science DepartmentStanford University 

Personalised recommendations