Abstract
This paper addresses the image semantic gap (i.e. the difficulty to automatically characterize the image semantic content through extracted low-level signal features) by investigating the formation of semantic concepts (such as mountains, sky, grass...) in a population of image agents:abstract structures representing the image visual entities. Through the development of processes mapping extracted low-level features to concept-based visual information, our contribution is twofold. First, we propose a learning framework mapping signal (color, texture) and semantic concepts to highlight the image agents. Contrary to traditional architectures considering high-dimensional spaces of low-level extracted signal features, this framework addresses the curse of dimensionality. Then, at the image agent population level, the agents communicate about the perceived semantic concepts with no access to global information or to the representations of other agents, they only exchange conceptual information. While doing so they adapt their internal representations to be more successful at conveying the perceived semantic information in future interactions. The image content is therefore soundly inferred through these concept-based linguistic interactions.
The SIR Agent prototype implements our theoretical framework and its architecture revolves around functional modules enabling the characterization of concept-based linguistic structures, highlighting the image agents and enforcing interactions and coordination between them.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Berlin, B., Kay, P.: Basic Color Terms: Their universality and Evolution. UC Press (1991)
Bhushan, N., et al.: The Texture Lexicon: Understanding the Categorization of Visual Texture Terms and Their Relationship to Texture Images. Cognitive Science 21(2), 219–246 (1997)
Blei, D., Jordan, M.: Modeling Annotated Data. ACM SIGIR, 127–134 (2003)
Bradshaw, B.: Semantic based image retrieval: a probabilistic approach. ACM MM, 167–176 (2000)
Egenhofer, M.: Reasoning about binary topological relations. In: Günther, O., Schek, H.-J. (eds.) SSD 1991. LNCS, vol. 525, pp. 143–160. Springer, Heidelberg (1991)
Feng, S., et al.: Multiple Bernoulli Relevance Models for image and video annotation. In: CVPR, pp. 1002–1009 (2004)
Gacogne, L.: Elements of fuzzy logics. Hermes Editions (1997)
Gong, Y., et al.: Image Indexing and Retrieval Based on Color Histograms. Multimedia Tools and App. II, 133–156 (1996)
Leow, W.K., Lai, S.Y.: Invariant matching of texture for content-based image retrieval. MMM, 53–68 (1997)
Lim, J., Jin, J.S.: A structured learning framework for content-based image indexing and visual query. Multimedia Systems 10(4), 317–331 (2005)
Miyahara, M., Yoshida, Y.: Mathematical Transform of (R,G,B) Color Data to Munsell (H,V,C) Color Data. In: SPIE, vol. 1001, pp. 650–657 (1988)
Platt, J.C.: Probabilities for Support Vector Machines. Advances in Large Margin Classifiers, pp. 61–74. MIT Press, Cambridge (1999)
Mojsilovic, A., Rogowitz, B.: Capturing image semantics with low-level descriptors. In: ICIP, pp. 18–21 (2001)
Smeulders, A., et al.: Content-based image retrieval at the end of the early years. IEEE PAMI 22(12), 1349–1380 (2000)
Srikanth, M., et al.: Exploiting Ontologies for Automatic Image Annotation. ACM SIGIR, 1349–1380 (2005)
Town, C.P., Sinclair, D.: CBIR Using Semantic Visual Categories. TR2000-14. AT&T Labs, Cambridge (2000)
Vapnik, V.: Statistical Learning Theory. Wiley, NYC (1998)
Zhou, X., Huang, T.: Unifying Keywords and Visual Contents in Image Retrieval. IEEE Multimedia 9(2), 23–33 (2002)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Belkhatir, M. (2008). An Agent Framework Based on Signal Concepts for Highlighting the Image Semantic Content. In: Bhowmick, S.S., Küng, J., Wagner, R. (eds) Database and Expert Systems Applications. DEXA 2008. Lecture Notes in Computer Science, vol 5181. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-85654-2_41
Download citation
DOI: https://doi.org/10.1007/978-3-540-85654-2_41
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-85653-5
Online ISBN: 978-3-540-85654-2
eBook Packages: Computer ScienceComputer Science (R0)