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.
Chapter PDF
Similar content being viewed by others
References
Henderson, J.: Introduction to real-world scene perception. Visual Cognition 12(3), 849–851 (2005)
Torralba, A., Oliva, A.: Statistics of natural image categories. Network: Computation in Neural Systems 14(3), 391–412 (2003)
Vogel, J., Schiele, B.: Semantic modeling of natural scenes for content-based image retrieval. Int. J. Comput. Vision 72(2), 133–157 (2007)
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)
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)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Perina, A., Cristani, M., Murino, V. (2008). Unsupervised Learning of Saliency Concepts for Natural Image Classification and Retrieval. In: Ruiz-Shulcloper, J., Kropatsch, W.G. (eds) Progress in Pattern Recognition, Image Analysis and Applications. CIARP 2008. Lecture Notes in Computer Science, vol 5197. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-85920-8_21
Download citation
DOI: https://doi.org/10.1007/978-3-540-85920-8_21
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-85919-2
Online ISBN: 978-3-540-85920-8
eBook Packages: Computer ScienceComputer Science (R0)