Abstract
The Web contains a wide variety of images published by the general public. Because the image is exposed as part of a Web page, the image is specified by not only the image content, but also the Web content using the image. This generates a gap between the content keywords and the usage keywords of the image. To fill the gap, we propose a concept of “context” of images in the Web. The context of an image is the set of Web contents (e.g. text and images) surrounding the image. We extend the notion of surroundings to include Web contents associated with the image by Web document structure and hyperlinks. We define different types of contexts for an image in accordance with types of associations between the image and the surrounding content. By visualizing context of each image, users can distinguish reliable image content among similar images based on the usage and/or reputation of the image. In this paper, we propose methods for searching and visualizing the context of images. We also propose a method for retrieving images based on their context.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Luhn, H.P.: Keyword in context index for technical literature (kwic index). American Documentation (11), 288–295 (1960)
Salton, G., McGill, M.: Introduction to modern information retrieval. McGraw Hill, New York (1983)
Lawrence, S.: Context in web search. IEEE Data Engineering Bulletin 23, 25–32 (2000)
Finklstein, L., Gabrilovich, E., Matias, Y., Rivlin, E., Solan, S., Wolfman, G., Ruppin, E.: Placing search in context: The concept revisited. ACM Transactions on Information Systems 20, 116–131 (2002)
Budzik, J., Hammond, K.J.: User interactions with everyday applications as context for just-in-time information access. In: Proceedings of the 2000 International Conference on Intelligent User Interfaces, pp. 41–51. ACM Press, New York (2000)
Google Image Search FAQ, http://www.google.com/help/faqimages.html
Altavista Help – Image Search, http://www.altavista.com/help/search/help_img
Frequently Asked Questions – Picture Search, http://www.alltheweb.com/help/faqs/picture_search.html
Harmandas, V., Sanderson, M., Dunlop, M.D.: Image retrieval by hypertext links. In: Proceedings of the ACM SIGIR 1997 Conference on Research and Development in Information Retrieval, pp. 296–303 (1997)
Furnas, G.: Generalized fisheye views. In: Proceedings of the ACM SIGCHI 1986 Conference on Human Factors in Computing Systems, pp. 16–23 (1986)
Mukherjea, S., Hara, Y.: Focus+context views of world-wide web nodes. In: Proceedings of ACM Hypertext 1997 Conference, pp. 187–196 (1997)
Lamping, J., Rao, R., Pirolli, P.: A focus+context technique based on hyperbolic geometry for visualizing large herarchies. In: Prceedings of the ACM SIGCHI 1995 Conference on Human Factors in Computing Systems, pp. 401–408 (1995)
Björk, S.: Hierarchical flip zooming: Enabling parallel exploration of hierarchical visualizations. In: Proceedings of the Working Conference on Advanced Visual Interfaces, pp. 232–237 (2000)
Korfhage, R.: Information Storage and Retrieval. John Wiley & Sons, Inc., Chichester (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zettsu, K., Kidawara, Y., Tanaka, K. (2003). Image Retrieval by Web Context: Filling the Gap between Image Keywords and Usage Keywords. In: Mařík, V., Retschitzegger, W., Štěpánková, O. (eds) Database and Expert Systems Applications. DEXA 2003. Lecture Notes in Computer Science, vol 2736. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45227-0_57
Download citation
DOI: https://doi.org/10.1007/978-3-540-45227-0_57
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40806-2
Online ISBN: 978-3-540-45227-0
eBook Packages: Springer Book Archive