Advertisement

Unsupervised Learning of Saliency Concepts for Natural Image Classification and Retrieval

  • A. Perina
  • M. Cristani
  • V. Murino
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5197)

Abstract

In this paper, a novel multi-scale, statistical approach for natural image representation is presented. The approach selects, at different scales, sets of features that represent exclusively the most typical visual elements of several natural scene categories, disregarding other non-characteristic, clutter, elements. Such features provide also a robust image visual signature, useful for scene understanding, image classification and retrieval. The approach lies upon a structured generative model efficiently trained through variational learning. Results regarding image classification and retrieval prove the goodness of the approach.

Keywords

Image analysis Image classification Unsupervised learning 

References

  1. 1.
    Henderson, J.: Introduction to real-world scene perception. Visual Cognition 12(3), 849–851 (2005)CrossRefGoogle Scholar
  2. 2.
    Torralba, A., Oliva, A.: Statistics of natural image categories. Network: Computation in Neural Systems 14(3), 391–412 (2003)CrossRefGoogle Scholar
  3. 3.
    Vogel, J., Schiele, B.: Semantic modeling of natural scenes for content-based image retrieval. Int. J. Comput. Vision 72(2), 133–157 (2007)CrossRefGoogle Scholar
  4. 4.
    Jordan, M.I., Ghahramani, Z., Jaakkola, T., Saul, L.K.: An introduction to variational methods for graphical models. Machine Learning 37(2), 183–233 (1999)CrossRefzbMATHGoogle Scholar
  5. 5.
    Müller, H., Müller, W., Squire, D.M., Marchand-Maillet, S., Pun, T.: Performance evaluation in content-based image retrieval: Overview and proposals. Pattern Recognition Letters 22(5), 593–601 (2001)CrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • A. Perina
    • 1
  • M. Cristani
    • 1
  • V. Murino
    • 1
  1. 1.Dipartimento di InformaticaUniversità degli studi di VeronaVeronaItalia

Personalised recommendations