Scene Categorization Using Topic Model Based Hierarchical Conditional Random Fields

  • Vikram Garg
  • Ehtesham Hassan
  • Santanu Chaudhury
  • Madan Gopal
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6744)

Abstract

We propose a novel hierarchical framework for scene categorization. The scene representation is defined by latent topics extracted by Latent Dirichlet Allocation. The interaction of these topics across scene categories is learned by probabilistic graphical modelling. We use Conditional Random Fields in a hierarchical setting for discovering the global context of these topics. The learned random fields are further used for categorization of a new scene. The experimental results of the proposed framework is presented on standard datasets and on image collection obtained from the internet.

Keywords

Scene categorization Latent dirichlet allocation Conditional random fields 

References

  1. 1.
    Lowe, D.G.: Object recognition from local scale-invariant features. In: Proceedings of the International Conference on Computer Vision, vol. 2, pp. 1150–1157 (2000)Google Scholar
  2. 2.
    Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent Dirichlet allocation. Journal of Machine Learning Research, 993–1022 (2003)Google Scholar
  3. 3.
    Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: Probabilistic models for segmenting and labelling sequence data. In: Proceedings of the International Conference on Machine Learning, pp. 282–289. Morgan Kaufmann, San Francisco (2001)Google Scholar
  4. 4.
    Yamaguchi, T., Maruyama, M.: Image categorization by a classifier based on probabilistic topic model. Pattern Recognition (2008)Google Scholar
  5. 5.
    Ergul, E., Arica, N.: Scene Classification Using Spatial Pyramid of Latent Topics. In: International Conference on Pattern Recognition (2010)Google Scholar
  6. 6.
    Fei, L.F., Persona, P.: A Bayesian Hierarchical Model for Learning Natural Scene Categories. In: IEEE Conference on Computer Vision and Pattern Recognition (2005)Google Scholar
  7. 7.
    Wang, C., Blei, D., Fei, L.F.: Simultaneous Image Classification and Annotation. In: IEEE Conference on Computer Vision and Pattern Recognition (2009)Google Scholar
  8. 8.
    Passino, G., Patras, I., Izquierdo, E.: Latent Semantic Local Distribution for CRF-based Image Semantic Segmentation. In: British Machine Vision Conference (2009)Google Scholar
  9. 9.
    Zhong, P., Wang, R.: Learning Conditional Random Fields for Classification of Hyperspectral Images. In: IEEE Transactions on Image Processing (2010)Google Scholar
  10. 10.
    Wang, X., Liu, X., Shi, Z., Shi, Z., Sui, H.: Voting Conditional Random Fields for Multi-label Image Classification. In: International Congress on Image and Signal Processing (2010)Google Scholar
  11. 11.
    Sivic, J., Russell, B.C., Zisserman, A., Freeman, W.T., Efros, A.A.: Unsupervised discovery of visual object class hierarchies. In: Computer Vision and Pattern Recognition (2008)Google Scholar
  12. 12.
    Sudderth, E.B., Torralba, A., Freeman, W.T., Willsky, A.S.: Learning Hierarchical Models of Scenes, Objects, and Parts. In: IEEE International Conference on Computer Vision (2005)Google Scholar
  13. 13.
    Wang, Y., Gong, S.: Conditional Random Field for Natural Scene Categorization. In: British Machine Vision Conference (2007)Google Scholar
  14. 14.
    Steyvers, M., Griffiths, T.: Matlab Topic Modelling Toolbox Version 1.3.2Google Scholar
  15. 15.
    Sarawagi, S.: CRF package, http://crf.sourceforge.net/

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Vikram Garg
    • 1
  • Ehtesham Hassan
    • 1
  • Santanu Chaudhury
    • 1
  • Madan Gopal
    • 1
  1. 1.Department of Electrical EngineeringIIT DelhiIndia

Personalised recommendations