Markov Random Fields and Spatial Information to Improve Automatic Image Annotation

  • Carlos Hernández-Gracidas
  • L. Enrique Sucar
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4872)


Content-based image retrieval (CBIR) is currently limited because of the lack of representational power of the low-level image features, which fail to properly represent the actual contents of an image, and consequently poor results are achieved with the use of this sole information. Spatial relations represent a class of high-level image features which can improve image annotation. We apply spatial relations to automatic image annotation, a task which is usually a first step towards CBIR. We follow a probabilistic approach to represent different types of spatial relations to improve the automatic annotations which are obtained based on low-level features. Different configurations and subsets of the computed spatial relations were used to perform experiments on a database of landscape images. Results show a noticeable improvement of almost 9% compared to the base results obtained using the k-Nearest Neighbor classifier.


Spatial relations Markov random fields automatic image annotation content-based image retrieval 


  1. 1.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 22, 888–905 (2000)CrossRefGoogle Scholar
  2. 2.
    Preston, C.: Gibbs States on Countable Sets. Cambridge University Press, Cambridge (1974)zbMATHGoogle Scholar
  3. 3.
    Spitzer, F.: Random Fields and Interacting Particle Systems. Mathematical Association of America (1971)Google Scholar
  4. 4.
    Allen, J.F.: Maintaining knowledge about temporal intervals. Communications of the ACM 26(11), 832–843 (1983)zbMATHCrossRefGoogle Scholar
  5. 5.
    Egenhofer, M., Sharma, J., Mark, D.: A critical comparison of the 4-intersection and 9-intersection models for spatial relations: Formal analysis. In: R.B., M., M., A. (eds.) Eleventh International Symposium on Computer-Assisted Cartography, Auto-Carto 11, Minneapolis, Minnesota, USA, pp. 1–11 (1993)Google Scholar
  6. 6.
    Chen, J., Li, Z., Li, C., Gold, C.: Describing topological relations with voronoi-based 9-intersection model. International Archives of Photogrammetry and Remote Sensing 32(4), 99–104 (1998)Google Scholar
  7. 7.
    Sistla, A., Yu, C., Haddack, R.: Reasoning about spatial relationships in picture retrieval systems. In: Bocca, J., Jarke, M., Zaniolo, C. (eds.) VLDB 1994. Twentieth International Conference on Very Large Data Bases, Santiago, Chile, pp. 570–581 (1994)Google Scholar
  8. 8.
    Zhang, Q., Yau, S.: On intractability of spatial relationships in content-based image database systems. Communications in Information and Systems 4(2), 181–190 (2004)zbMATHMathSciNetGoogle Scholar
  9. 9.
    Zhang, Q., Chang, S., Yau, S.: On consistency checking of spatial relationships in content-based image database systems. Communications in Information and Systems 5(3), 341–366 (2005)zbMATHMathSciNetGoogle Scholar
  10. 10.
    Hollink, L., Nguyen, G., Schreiber, G., Wielemaker, J., Wielinga, B., Worring, M.: Adding spatial semantics to image annotations. In: SemAnnot 2004. Fourth International Workshop on Knowledge Markup and Semantic Annotation, Hiroshima, Japan. LNCS, Springer, Heidelberg (2004)Google Scholar
  11. 11.
    Rathi, V., Majumdar, A.: Content based image search over the world wide web. In: Chaudhuri, S., Zisserman, A., Jain, A., Majumder, K. (eds.) ICVGIP 2002. Third Indian Conference on Computer Vision, Graphics and Image Processing, Ahmadabad, India (2002)Google Scholar
  12. 12.
    Ren, W., Singh, M., Singh, S.: Image retrieval using spatial context. In: Wellstead, P. (ed.) IWSSIP 2002. Ninth International Workshop on Systems, Signals and Image Processing, Manchester, UK, vol. 18, pp. 44–49 (2002)Google Scholar
  13. 13.
    Neapolitan, R.: Probabilistic Reasoning in Expert Systems. Wiley, New York (1990)Google Scholar
  14. 14.
    Kirkpatrick, S., Gelatt, C., Vecchi, M.: Optimization by simulated annealing. Science 220(4598), 671–680 (1983)CrossRefMathSciNetGoogle Scholar
  15. 15.
    Carbonetto, P.: Unsupervised statistical models for general object recognition. Msc thesis, The Faculty of Graduate Studies, Department of Computer Science, The University of British Columbia, West Mall Vancouver, BC Canada (2003)Google Scholar
  16. 16.
    Escalante, H., Montes, M., Sucar, L.: Word co-occurrence and markov random fields for improving automatic image annotation. In: Rajpoot, N.M., B.A. (eds.) BMVC 2007. Eighteenth British Machine Vision Conference, Warwick, UK, vol. 2, pp. 600–609 (2007)Google Scholar
  17. 17.
    Bäck, T.: Evolutionary Algorithms in Theory and Practice: Evolution Strategies, Evolutionary Programming, Genetic Algorithms. Oxford Univ. Press, Oxford (1996)zbMATHGoogle Scholar
  18. 18.
    Wellington, C., Courville, A., Stentz, A.: Interacting markov random fields for simultaneous terrain modeling and obstacle detection. In: Thrun, S., Sukhatme, G., Schaal, S. (eds.) RSS 2005. Robotics: Science and Systems, Boston, USA, pp. 1–8 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Carlos Hernández-Gracidas
    • 1
  • L. Enrique Sucar
    • 1
  1. 1.National Institute of Astrophysics, Optics and Electronics, Luis Enrique Erro #1, Sta. María Tonantzintla, PueblaMéxico

Personalised recommendations