An integrative semantic framework for image annotation and retrieval


Most public image retrieval engines utilise free-text search mechanisms, which often return inaccurate matches as they in principle rely on statistical analysis of query keyword recurrence in the image annotation or surrounding text. In this paper we present a semantically-enabled image annotation and retrieval engine that relies on methodically structured ontologies for image annotation, thus allowing for more intelligent reasoning about the image content and subsequently obtaining a more accurate set of results and a richer set of alternatives matchmaking the original query. Our semantic retrieval technology is designed to satisfy the requirements of the commercial image collections market in terms of both accuracy and efficiency of the retrieval process. We also present our efforts in further improving the recall of our retrieval technology by deploying an efficient query expansion technique.

Publication DOI:
Divisions: College of Engineering & Physical Sciences > School of Informatics and Digital Engineering > Computer Science
Additional Information: © 2007 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Event Title: IEEE/WIC/ACM International Conference on Web Intelligence, WI 2007
Event Type: Other
Event Dates: 2007-11-02 - 2007-11-05
Uncontrolled Keywords: Artificial Intelligence,Computer Networks and Communications
ISBN: 0769530265, 9780769530260
Full Text Link: http://wwwusers ... di/WI07_sub.pdf
Related URLs: http://www.scop ... tnerID=8YFLogxK (Scopus URL)
http://wwwusers ... di/WI07_sub.pdf (Organisation URL)
https://ieeexpl ... cument/4427064/ (Publisher URL)
PURE Output Type: Conference contribution
Published Date: 2008-01-07
Authors: Osman, Taha
Thakker, Dhavalkumar
Schaefer, Gerald
Lakin, Phil



Version: Accepted Version

| Preview

Export / Share Citation


Additional statistics for this record