Abstract
This paper investigates the use of qualitative and spatially expressive semantic descriptions for image classification. In particular, it addresses the question of how a qualitative representation performs compared to a more quantitative one, using a semantic based symbolic approach. The approach is based on using different qualitative spatial representations applied to local semantic concepts such as grass, sky, water etc in a corpus of natural scenes images, to learn qualitative class descriptions and categorise them into one of six semantically meaningful classes such as coasts, forest etc. Three kinds of qualitative spatial relations, namely Allen’s relations [1] applied on the vertical axis of images, chord representation [9] applied on segmented semantically labelled image regions, and relative size of semantic concepts in each image have been investigated. A number of well-known supervised learning techniques have been applied to determine their usefulness. It is shown that a purely qualitative representation can result into better image description and perform at the similar level or even slightly better, compared to an existing largely quantitative representation [20]. Such qualitative and spatially expressive descriptions may therefore have utility in semantic querying and image retrieval systems.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Allen, J. F. “Maintaining knowledge about temporal intervals” In Communications of ACM, vol. 26, no. 11, November 1983.
Boutell, M., Luo, J., Shen, X., and Brown, C. “Learning multi-label scene classification”. Pattern Recognition, vol. 37, no.9, pp. 1757–1771, September 2004.
Cristianini, N. and Shaw-Taylor, J. «An introduction to support vector machines and other kernel based methods». Cambridge University Press, 2000.
Freund, Y., and Schapire, E. R. «Experiments with a new boosting algorithm». Proceedings of Thirteenth International Conference on Machine Learning, pp. 148–156, 1996.
Gorkani, M.M., and Picard, W.R. »Texture orientation for sorting photos at a glance». In Proceedings of International Conference on Pattern Recognition, Vol.1, pp. 459–464, Jerusalem, Israel, October 1994.
Maron, O. and Lakshmi Ratan, A. «Multiple-instance learning for natural scene classification». In Proceedings of 15th International Conference on Machine Learning, PP 341–349, 1998.
Maron, O., and Lozano-Pe’rez, T. «A framework for multiple instance learning». Advances in Neural Information Processing Systems, 10,1998.
Mao, J., and Jain, A.K. «Texture classification and segmentation using multiresolution simultaneous autoregressive models». Pattern Recognition, Vol. 25, No. 2, Pp 173–188, 1992.
Mörchen, F., Ultsch, A.: Discovering Temporal Knowledge in Multivariate Time Series, Weihs, C, Gaul, W. (Eds), In Classification; The Ubiquitous Challenge, Proceedings 28th Annual Conference of the German Classification Society (GfKl 2004), Dortmund, Germany, Springer, Heidelberg, (2005), pp. 272–279.
Mukerjee, A., and Joe, G. «A Qualitative Model for Space». In Proceedings of AAAI-90, Morgan Kaufmann Publishers, pp 721–727, 1990.
Oliva, A., Torralba, A., Guerin-Dugue, A., and Herault, A. «Global semantic classification of scenes using power spectrum templates». In Challenges of Image Retrieval CIR. Newcastle UK, 1999.
Pal, N.R. and Pal, S.K. «A review of image segmentation techniques». Pattern Recognition, Vol. 26, Pp. 1277–1294, 1993.
Picard, R., and Minka, T. «Vision texture for annotation». ACM Journal of Multimedia Systems, 1995.
Quinlan, J.R. «C 4.5: Programs for machine learning». Morgan Kaufman Publishers, Inc. 1993.
Szummer, M., and Picard, R. «Indoor outdoor image classification». In Workshop on Content-based Access of Image and Video Databases. Bombay, India, January 1998.
Serrano, N., Savakis, A., and Luo, J. «Improved scene classification using efficient low level features and semantic cues». Pattern Recognition, vol. 37, no. 9, pp. 1773–1784, September 2004.
Town, C, and Sinclair, D. “Content-based image retrieval using semantic visual categories”. Tech. Report 2000.14, AT&T Laboratories Cambridge, 2000.
Vailaya, A., Jain, A., and Zhang, H. «On image classification: cit vs landscape». Pattern Recognition, vol 31, no. 12, pp. 1921–1935, December 1998.
Vailaya, A., Figueiredo, M., Jain, A., and Zhang, H.J. «Bayesian Framework for Hierarchical Semantic Classification of Vacation Images». IEEE International Conference on Multimedia Computing and Systems, pp. 518–523 vol.1, 1999.
Vogel, J., and Schiele, B. «A semantic typicality measure for natural scene categorization». In: Pattern Recognition Symposium DAGM 2004, Tubingen, Germany, September 2004.
Vogel, J. «Semantic scene modelling and retrieval». PhD Thesis of Julia Vogel, selected Readings in Vision and Graphics, Vol. 33, Hartung-Gorre Verlag Konstanz, 2004.
Walischewski, H. «Learning regions of interest in postal automation». In roceedings of 5th International Conference on Document Analysis and Recognition (ICDAR’99), 1999, Bangalore, India.
Witten, LH., and Frank, E. «Data Mining, Practical machine learning tools and techniques with JAVA implementations». Morgan Kaufman Publishers, 2000.
Frank, E. and Witten, LH. «Generating Accurate Rule Sets Without Global Optimization.» In Shavlik, J., ed., Machine Learning: Proceedings of the Fifteenth International Conference, Morgan Kaufmann Publishers, 1998.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Springer-Verlag London Limited
About this paper
Cite this paper
Qayyum, Z.U., Cohn, A.G. (2007). Qualitative Approaches to Semantic Scene Modelling and Retrieval. In: Bramer, M., Coenen, F., Tuson, A. (eds) Research and Development in Intelligent Systems XXIII. SGAI 2006. Springer, London. https://doi.org/10.1007/978-1-84628-663-6_25
Download citation
DOI: https://doi.org/10.1007/978-1-84628-663-6_25
Publisher Name: Springer, London
Print ISBN: 978-1-84628-662-9
Online ISBN: 978-1-84628-663-6
eBook Packages: Computer ScienceComputer Science (R0)