Image Annotation Refinement Using Web-Based Keyword Correlation

  • Ainhoa Llorente
  • Enrico Motta
  • Stefan Rüger
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5887)


This paper describes a novel approach that automatically refines the image annotations generated by a non-parametric density estimation model. We re-rank these initial annotations following a heuristic algorithm, which uses semantic relatedness measures based on keyword correlation on the Web. Existing approaches that rely on keyword co-occurrence can exhibit limitations, as their performance depend on the quality and coverage provided by the training data. Additionally, WordNet based correlation approaches are not able to cope with words that are not in the thesaurus. We illustrate the effectiveness of our Web-based approach by showing some promising results obtained on two datasets, Corel 5k, and ImageCLEF2009.


Automated image annotation Normalized Google Distance semantic similarity 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Jin, R., Chai, J.Y., Si, L.: Effective automatic image annotation via a coherent language model and active learning. In: Proceedings of the 12th International ACM Conference on Multimedia, pp. 892–899 (2004)Google Scholar
  2. 2.
    Jin, Y., Khan, L., Wang, L., Awad, M.: Image annotations by combining multiple evidence & WordNet. In: Proceedings of the 13th International ACM Conference on Multimedia, pp. 706–715 (2005)Google Scholar
  3. 3.
    Liu, J., Li, M., Ma, W.Y., Liu, Q., Lu, H.: An adaptive graph model for automatic image annotation. In: Proceedings of the 8th ACM International Workshop on Multimedia Information Retrieval, pp. 61–70 (2006)Google Scholar
  4. 4.
    Zhou, X., Wang, M., Zhang, Q., Zhang, J., Shi, B.: Automatic image annotation by an iterative approach: incorporating keyword correlations and region matching. In: Proceedings of the International ACM Conference on Image and Video Retrieval, pp. 25–32 (2007)Google Scholar
  5. 5.
    Llorente, A., Rüger, S.: Using second order statistics to enhance automated image annotation. In: Boughanem, M., et al. (eds.) ECIR 2009. LNCS, vol. 5478, pp. 570–577. Springer, Heidelberg (2009)Google Scholar
  6. 6.
    Wang, C., Jing, F., Zhang, L., Zhang, H.J.: Image annotation refinement using random walk with restarts. In: Proceedings of the 14th annual ACM International Conference on Multimedia, pp. 647–650. ACM, New York (2006)CrossRefGoogle Scholar
  7. 7.
    Jin, Y., Wang, L., Khan, L.: Improving image annotations using WordNet. In: Candan, K.S., Celentano, A. (eds.) MIS 2005. LNCS, vol. 3665, pp. 115–130. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  8. 8.
    Liu, J., Wang, B., Li, M., Li, Z., Ma, W., Lu, H., Ma, S.: Dual cross-media relevance model for image annotation. In: Proceedings of the 15th International Conference on Multimedia, pp. 605–614 (2007)Google Scholar
  9. 9.
    Cilibrasi, R., Vitanyi, P.: The Google similarity distance. IEEE Transactions on Knowledge and Data Engineering 19(3), 370–383 (2007)CrossRefGoogle Scholar
  10. 10.
    Gracia, J., Mena, E.: Web-based measure of semantic relatedness. In: Bailey, J., Maier, D., Schewe, K.-D., Thalheim, B., Wang, X.S. (eds.) WISE 2008. LNCS, vol. 5175, pp. 136–150. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  11. 11.
    Yavlinsky, A., Schofield, E., Rüger, S.: Automated image annotation using global features and robust nonparametric density estimation. In: Proceedings of the International ACM Conference on Image and Video Retrieval, pp. 507–517 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Ainhoa Llorente
    • 1
  • Enrico Motta
    • 1
  • Stefan Rüger
    • 1
  1. 1.Knowledge Media InstituteThe Open UniversityMilton KeynesU.K.

Personalised recommendations