A Novel Image Auto-annotation Based on Blobs Annotation

  • Mahdia Bakalem
  • Nadjia Benblidia
  • Sami Ait-Aoudia
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 102)


At present, there are vast amounts of digital media available on the web. In the Web image retrieval, the semantics of an image is a big problem, generally, the search engines index the text associated to the image of Web pages. This text doesn’t correspond really to them.

The image annotation is an effective technology for improving the Web image retrieval. Indeed, it permits assigning semantics to an image, by attributing to the images keywords corresponding to the senses conveyed by these images. To improve the automatic image annotation (AIA), a strategy consists in correlating the textual and visual information of the images. In this work, we propose an image auto-annotation system based on AnnotB-LSA algorithm that integrates the LSA model.

The main focus of this paper is two-fold. First, in the training stage, we perform clustering of regions into classes of similar visual regions called blobs according to their visual feature. This clustering prepares a visual space by learning from the annotated images corpus and permits to annotate the blobs by performing the algorithm annotB-LSA. Second, in the new image annotation stage, we can annotate a new image by selecting the key words of the blobs to which its regions belong. Experiment results show that our proposed system is performing.


Visual Feature Latent Semantic Analysis Region Cluster Image Annotation Information Retrieval System 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Monay, F., Gatica-Perez, D.: One Picture Auto Annotation with Latent Space Models. In: Proc. ACM Int. Conf. one Multimedia (ACM MESSRS), Berkeley, California, USA (2003)Google Scholar
  2. 2.
    Monay, F., Gatica-Perez, D.: PLSA-based Auto-Annotation Picture: Constraining the Latent Space. In: Proc. ACM Int. Conf. one Multimedia (ACM MESSRS), NewYork, USA (2004)Google Scholar
  3. 3.
    Tollari, S.: Indexing and Research of pictures by Fusion of Textual and Visual information. Thesis of doctorate. University of the south Toulan-Var (2006)Google Scholar
  4. 4.
    Weber, R., Schek, H.-J., Blott, S.: In Quantitative Analysis and Performance Study heart Similarity-Search Methods in High-Dimensional Space. In: Proceedings of International Conference of Very Large Dated Bases (VLDB), pp. 194–205 (1998)Google Scholar
  5. 5.
    Zhao, Y., Zhao, Y., Zhu, Z., Flap, S.: TO Novel Picture Annotation Design Based one Neural Network. In: Eighth International Conference one Intelligent Systems Design and Applications. IEEE, Los Alamitos (2008), 978-0-7695-3382-7/08, doi:10.1109/ISDA.55Google Scholar
  6. 6.
    Khan, L.: Standards heart Picture Annotation using Semantic Web. To compute Standards & Interfaces 29, 169–204 (2007)Google Scholar
  7. 7.
    Xiao, Y., Chua, T.-S., Lee, C.-H.: Fusion of region and image-based techniques for automatic image annotation. In: Cham, T.-J., Cai, J., Dorai, C., Rajan, D., Chua, T.-S., Chia, L.-T. (eds.) MMM 2007. LNCS, vol. 4351, pp. 247–258. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  8. 8.
    Wang, X.-J., Zhang, L., Jing, F., There, W.-Y.: My. AnnoSearch: Auto-Annotation picture Search by. In: Proceedings of the 2006 IEEES Computer Society Conference one to Compute Vision and Pattern Recognition, June 17-22 (2006)Google Scholar
  9. 9.
    Lu, J., Zhao, T., Zhang, Y.: Feature Based Selection One Genetic Algorithm heart Picture Annotation. Knowledge-Based Systems (2008), 0950-7051Google Scholar
  10. 10.
    Jin, W., Shi, R., Chua, S.T.: In Semi-Naive Bayesian Method Incorporating Clustering with Even-Wise Constraints heart Auto Picture Annotation. In: MM 2004, October 10-16. ACM, New York (2004)Google Scholar
  11. 11.
    Jeon, J., Lavrenko, V., Manmatha, R.: Automatic Image Annotation and Retrieval using Cross-Media Relevance Models. In: SIGIR 2003. ACM Press, Toronto (2003), 1-58113-646-3/03/0007Google Scholar
  12. 12.
    Deerwester, S., Dumais, S.T., Furnas, G.W., Landauer, T.K., Harshman, R.: Indexing by Latent Semantic Analysis. Newspaper of the American Society of Information Science 41(6), 391–407 (1990)CrossRefGoogle Scholar
  13. 13.
    Barnard, K., Duygulu, P., Freitas, N., Forsyth, D., Blei, D., Jordan, I.: Matching words and pictures. Newspaper of Plots Learning Research 3, 1107–1135 (2003)zbMATHCrossRefGoogle Scholar
  14. 14.
    Shi, J., Malik, J.: Normalized Cuts and Picture Segmentation. IEEE Transactions one pattern Analysis and Plots Intelligence 22(8), 888–905 (2000)CrossRefGoogle Scholar
  15. 15.
    Liu, W., Tang, X.: Learning an Image-Word Embedding for Image Auto-Annotation on the Nonlinear Latent Space. In: MM 2005, November 6-11. ACM, Singapore (2005), 1-59593-044-2/05/0011Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Mahdia Bakalem
    • 1
  • Nadjia Benblidia
    • 2
  • Sami Ait-Aoudia
    • 3
  1. 1.Laboratory Research for the Development of Computing SystemsSaad Dahlab University Blida, Algeria Laboratory Research On the, Image Processing High Computing School - ESI Oued smartAlgeria
  2. 2.Laboratory Research for the Development of Computing SystemsSaad Dahlab University BlidaAlgeria
  3. 3.Laboratory Research On the Image Processing High Computing School - ESI Oued smartAlgeria

Personalised recommendations