Giving meanings to WWW images

ABSTRACT

Images are increasingly being embedded in HTML documents on the WWW. Such documents over the WWW essentially provides a rich source of image collection from which user can query. Interestingly, the semantics of these images are typically described by their surrounding text. Unfortunately, most WWW image search engines fail to exploit these image semantics and give rise to poor recall and precision performance. In this paper, we propose a novel image representation model called Weight ChainNet. Weight ChainNet is based on lexical chain that represents the semantics of an image from its nearby text. A new formula, called list space model, for computing semantic similarities is also introduced. To further improve the retrieval effectiveness, we also propose two relevance feedback mechanisms. We conducted an extensive performance study on a collection of 5000 images obtained from documents identified by more than 2000 URLs. Our results show that our models and methods outperform existing technique. Moreover, the relevant feedback mechanisms can lead to significantly better retrieval effectiveness.

REFERENCES

• 1: Suliman Al-Hawamdeh , B. C. Ooi , R. Price , T. H. Tng , Y. H. Ang , L. Hui, Nearest neighbour searching in a picture archive system, International conference on Multimedia information systems '91, p.17-34, November 1991, Jurong, Singapore
• 2: A. E. Cawkell, Imaging systems and picture collection management: a review, Information Services and Use, v.12 n.4, p.301-325, July 1992
• 3: Rosanne Price , Tat-seng Chua , Suliman Al-Hawamdeh, Applying relevance feedback to a photo archival system, Journal of Information Science, v.18 n.3, p.203-215, 1992 [doi>10.1177/016555159201800305]
• 4: John R. Smith , Shih-Fu Chang, VisualSEEk: a fully automated content-based image query system, Proceedings of the fourth ACM international conference on Multimedia, p.87-98, November 18-22, 1996, Boston, Massachusetts, United States [doi>10.1145/244130.244151]
• 5: T.S. Chua and W.C. Low. Image retrieval using multiple features and domain knowledge. In proceeding of International Symposium on Multimedia Information Processing, Dec, 1997, Pages 543-548
• 6: W.Niblack, R.Barber, and W.Equitz. the qbib project: querying images by content using color, texture, and shape. Technical report, IBM RJ 9203(81511), Feb, 1993
• 7: Greg Pass , Ramin Zabih , Justin Miller, Comparing images using color coherence vectors, Proceedings of the fourth ACM international conference on Multimedia, p.65-73, November 18-22, 1996, Boston, Massachusetts, United States [doi>10.1145/244130.244148]
• 8: Michael J. Swain , Dana H. Ballard, Color indexing, International Journal of Computer Vision, v.7 n.1, p.11-32, Nov. 1991 [doi>10.1007/BF00130487]
• 9: T. S. Chua , W. C. Low , C. X. Chu, Relevance Feedback Techniques for Color-based Image Retrieval, Proceedings of the 1998 Conference on MultiMedia Modeling, p.24, October 12-15, 1998
• 10: Mark,E. Frisse, Searching for information in a hypertext medical handbook, Communications of the ACM, v.31 n.7, p.880-886, July 1988 [doi>10.1145/48511.48518]
• 11: H. P. Frei , D. Stieger, Making use of hypertext links when retrieving information, Proceedings of the ACM conference on Hypertext, p.102-111, November 30-December 04, 1992, Milan, Italy [doi>10.1145/168466.168502]
• 12: W. Bruce Croft , Howard R. Turtle, Retrieval strategies for hypertext, Information Processing and Management: an International Journal, v.29 n.3, p.313-324, May–June, 1993 [doi>10.1016/0306-4573(93)90058-L]
• 13: M. D. Dunlop , C. J. van Rijsbergen, Hypermedia and free text retrieval, Information Processing and Management: an International Journal, v.29 n.3, p.287-298, May–June, 1993 [doi>10.1016/0306-4573(93)90056-J]
• 14: Maristella Agosti, Information Retrieval and HyperText, Kluwer Academic Publishers, Norwell, MA, 1996
• 15: V. Harmandas , M. Sanderson , M. D. Dunlop, Image retrieval by hypertext links, Proceedings of the 20th annual international ACM SIGIR conference on Research and development in information retrieval, p.296-303, July 27-31, 1997, Philadelphia, Pennsylvania, United States
• 16: Dunlop M.D. (1991). Multimedia Information Retrieval, Ph.D. Thesis. Computing Science Department, University of Glasgow, Report 1991/R21.
• 17: Jane Morris , Graeme Hirst, Lexical cohesion computed by thesaural relations as an indicator of the structure of text, Computational Linguistics, v.17 n.1, p.21-48, March 1991
• 18: Shih-Fu Chang, William Chen, and Hari Sundaram, Semantic Visual Template - Linking Visual Fetures to Semantics. IEEE Intern Conference on Image Processing, Chicago IL, Oct 1998
• 19: G.A. Miller, R. Beckwith, C. Felbaum, D. Gross and K. Miller, Introduction to WordNet: An On-line Lexical Database. Revised Version 1993.
• 20: Ellen M. Voorhees and Yuan-Wang Hou, "Vector Expansion in a Large Collection", First Text REtrieval Conference (TREC- 1), 1993.
• 21: Ellen M. Voorhees, Query expansion using lexical-semantic relations, Proceedings of the 17th annual international ACM SIGIR conference on Research and development in information retrieval, p.61-69, July 03-06, 1994, Dublin, Ireland
• 22: Kian-Lee Tan , Beng Chin Ooi , Chia Yeow Yee, An Evaluation of Color-Spatial Retrieval Techniques for Large Image Databases, Multimedia Tools and Applications, v.14 n.1, p.55-78, May 2001 [doi>10.1023/A:1011359607594]
• 23: Beng Chin Ooi , Kian-Lee Tan , Tat Seng Chua , Wynne Hsu, Fast image retrieval using color-spatial information, The VLDB Journal — The International Journal on Very Large Data Bases, v.7 n.2, p.115-128, May 1998 [doi>10.1007/s007780050057]

INDEX TERMS

Keywords:
WWW, image representation, image retrieval, relevance feedback, semantic similarity