Exploiting Problem Domain Knowledge for Accurate Building Image Classification

  • Andres Dorado
  • Ebroul Izquierdo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3115)

Abstract

An approach for classification of building images through rule-based fuzzy inference is presented. It exploits rough matching and problem domain knowledge to improve precision results. This approach uses knowledge representation based on a fuzzy reasoning model for establishing a bridge between visual primitives and their interpretations.

Knowledge representation goes from low level to high level features. The knowledge is acquired from both visual content and users. These users provide the interpretations of low level features as well as their knowledge and experience to improve the rule base.

Experiments are tailored to building image classification. This approach can be extended to other semantic categories, i.e. skyline, vegetation, landscapes. Results show that proposed method is promising support for semantic annotation of image/video content.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Dorai, C., Venkatesh, S.: Bridging the Semantic Gap with Computational Media Aesthetics. IEEE Multimedia 10(2), 15–17 (2003)CrossRefGoogle Scholar
  2. 2.
    Ishibuchi, J., Nakashima, T.: Effect of Rule Weights in Fuzzy Rule-Based Classification Systems. IEEE Trans. on Fuzzy Systems 9(4), 506–515 (2001)CrossRefGoogle Scholar
  3. 3.
    Iqbal, Q., Aggarwal, J.K.: Applying Perceptual Grouping to Content-Based Image Retrieval: Building Images. In: Proc. IEEE Int’l Conf. on Computer Vision and Pattern Recognition (CVPR 1999), vol. 1, pp. 42–48 (1999)Google Scholar
  4. 4.
    Vailaya, A., Figueiredo, M.A.T., Jain, A.K., Zhang, H.-J.: Image Classification for Content-Based Indexing. IEEE Trans. on Image Processing 10(1), 117–130 (2001)MATHCrossRefGoogle Scholar
  5. 5.
    Wang, Y.-N., Chen, L.-B., Hu, B.-G.: Semantic Extraction of the Building Images using Support Vector Machines. In: Proc. IEEE Int’l Conf. on Machine Learning and Cybernetics, vol. 3, pp. 1608–1613 (2002)Google Scholar
  6. 6.
    Dorado, A., Izquierdo, E.: Semantic Labeling of Images Combining Color, Texture and Keywords. In: Proc. IEEE Int’l Conf. on Image Processing (ICIP 2003), vol. 3, pp. 9–12 (2003)Google Scholar
  7. 7.
    Zeljkovic, V., Dorado, A., Izquierdo, E.: A Modified Shading Model Method for Building Detection. In: 5th Int’l Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS 2004) (2004) (to appear)Google Scholar
  8. 8.
    Dorado, A., Calic, J., Izquierdo, E.: A Rule-Based Video Annotation System. IEEE Trans. on Circuits and Systems for Video Technology (2004) (to appear)Google Scholar
  9. 9.
    Choi, Y., Won, C.S., Ro, Y.M., Manjunath, B.S.: Texture Descriptors. In: Manjunath, B.S., Salembier, P., Sikora, T. (eds.) Introduction to MPEG-7, Multimedia Content Description Interface. ch.14, pp. 213–229. Wiley, Chichester (2002)Google Scholar
  10. 10.
    TRECVID: TREC Video Retrieval Evaluation (2003), http://www-nlpir.nist.gov/projects/trecvid/

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Andres Dorado
    • 1
    • 2
  • Ebroul Izquierdo
    • 2
  1. 1.School of EngineeringPontificia Universidad JaverianaColombia
  2. 2.Electronic Engineering DepartmentQueen Mary,University of LondonLondonUK

Personalised recommendations