An adaptive approach for image organisation and retrieval

Urban, J., Jose, J.M. and van Rijsbergen, C.J. (2003) An adaptive approach for image organisation and retrieval. In: Third International Workshop on Content-Based Multimedia Indexing (CBMI'03), Rennes, France, 22-24 September 2003, pp. 119-126.

Abstract

We propose and evaluate an adaptive approach towards content-based image retrieval (CBIR), which is based on the Ostensive Model of developing information needs. We use ostensive relevance to capture the user's current interest and tailor the retrieval accordingly. Our approach supports content-assisted browsing, by incorporating an adaptive query learning scheme based on implicit feedback from the user. Textual and colour features are employed to characterise images. Evidence from these features are combined using the Dempster-Shafer theory of evidence combination. Results from a user-centred, task-oriented evaluation show that the ostensive interface is preferred over a traditional interface with manual query facilities. Its strengths are considered to lie in its ability to adapt to the user's need, and its very intuitive and fluid way of operation.

• Item Type: Conference Proceedings
• Keywords: image retrieval, relevance feedback, ostensive browser, user evaluation
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Jose, Professor Joemon
• Authors: Urban, J., Jose, J.M., and van Rijsbergen, C.J.
• Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science; Q Science > QA Mathematics > QA76 Computer software
• College/School: College of Science and Engineering > School of Computing Science
• Research Group: Information Retrieval
• Copyright Holders: Copyright © 2003 The Authors
• First Published: First published in Proceedings of the Third International Workshop on Content-Based Multimedia Indexing (CBMI'03)
• Publisher Policy: Reproduced with permission of the authors