Abstract
Using low-level features to support semantic search of images is a difficult task. As a result, textual content is used to provide semantic description or annotation of images. Such textual description of what we may call as ‘surrounding text’ is a value added features available in most web images particularly on-line news images. Most search engines used them as a feature to provide textual meaning of images. Relying on surrounding text alone, however, unable to provide support for semantic search that go beyond indexed terms. Lexical resources and ontology are potential sources to enhance searching for images. This paper discusses the use of WordNet and ConceptNet to enhance searching for on-line news images. This is further improved with named entity recognition (NER) technique to annotate important entities such as name if a person, location and organization among image searchers. Results show that lexical ontology has the capacity to semantically enhance the meanings of conventional bag of words index.
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
Benitez, A.B., Chang, S.-F.: Semantic Knowledge Construction from Annotated Image Collections, Multimedia and Expo, 2002. In: ICME 2002: Proceedings 2002 IEEE International Conference, vol. 2, pp. 205–208. IEEE Press, New York (2002)
Miller, G.A.: WordNet: A Lexical Database for English. Communication of the ACM 38(11), 39–41 (1995)
Liu, H., Singh, P.: ConceptNet – A Practical Commonsense Reasoning Toolkit. BT Technology Journal 22(4), 211–226 (2002)
Noah, S.A., Azilawati, A., Tengku Sembok, T.M., Tengku Siti Meriam, T.W.: Exploiting Surrounding Text for Retrieving Web Images. Journal of Computer Science 4(10), 842–846 (2009)
Liu, H., Lieberman, H.: Robust Photo Retrieval Using World Semantics. In: Proceedings of the LREC 2002 Workshop on Creating and Using Semantics for Information Retrieval and Filtering, pp. 15–20 (2002)
Gong, Z., Leong, H.U., Cheang, C.W.: Web Image Indexing by Using Associated Data. Knowledge and Information Systems 10(2), 243–264 (2006)
Hua, Z., Wang, X.-J., Lui, Q., Lu, H.: Semantic Knowledge Extraction and Annotation for Web Image. In: Proceedings of the 13th Annual ACM International Conference on Multimedia, pp. 467–470. ACM Press, New York (2005)
Hsu, M.-H., Chen, H.-H.: Information Retrieval with Commonsense Knowledge. In: Proceedings of the 29th Annual International SIGIR Conference, pp. 651–652. ACM Press, New York (2006)
Kuo, C.-H., Chou, T.-C., Tsao, N.-L., Lan, Y.-H.: CANFIND: A Semantic Image Indexing and Retrieval System. In: Proceedings of the 2003 International Symposium on Circuits and Systems, vol. 2, pp. 644–647. IEEE Press, New York (2003)
Kawata, K., Sakai, H., Masuyama, S.: QUARK: A Question and Answering System Using Newspaper Corpus as a Knowledge Source. In: Proceeding of the 3rd NTCIR Workshop, National Institute of Informatics, Tokyo (2003)
Baeza-Yates, R., Ribeiro-Neto, B.: Modern Information Retrieval. Addison-Wesley, New York (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Noah, S.A., Ali, D.A. (2010). The Role of Lexical Ontology in Expanding the Semantic Textual Content of On-Line News Images. In: Cheng, PJ., Kan, MY., Lam, W., Nakov, P. (eds) Information Retrieval Technology. AIRS 2010. Lecture Notes in Computer Science, vol 6458. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-17187-1_18
Download citation
DOI: https://doi.org/10.1007/978-3-642-17187-1_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-17186-4
Online ISBN: 978-3-642-17187-1
eBook Packages: Computer ScienceComputer Science (R0)