Mind the gap: another look at the problem of the semantic gap in image retrieval

Hare, J.S., Lewis, P.H., Enser, P.G.B. and Sandom, C.J. (2006) Mind the gap: another look at the problem of the semantic gap in image retrieval In: Chang, E.Y., Hanjalic, A. and Sebe, N., eds. Proceedings of multimedia content analysis, management and retrieval 2006. SPIE. ISBN 081946113X

[img]PDF
Restricted to Registered users only

659Kb

Abstract

This paper attempts to review and characterise the problem of the semantic gap in image retrieval and the attempts being made to bridge it. In particular, we draw from our own experience in user queries, automatic annotation and ontological techniques. The first section of the paper describes a characterisation of the semantic gap as a hierarchy between the raw media and full semantic understanding of the media’s content. The second section discusses real users’ queries with respect to the semantic gap. The final sections of the paper describe our own experience in attempting to bridge the semantic gap. In particular we discuss our work on auto-annotation and semantic-space models of image retrieval in order to bridge the gap from the bottom up, and the use of ontologies, which capture more semantics than keyword ob ject labels alone, as a technique for bridging the gap from the top down.

Item Type:Chapter in book
Uncontrolled Keywords:Semantic Gap; Image Retrieval; Automatic Annotation; Ontologies; Cross Language Latent Semantic Indexing
Subjects:P000 Mass Communications and Documentation > P100 Information Services
Faculties:Faculty of Science and Engineering > School of Computing, Engineering and Mathematics > Visual Image Retrieval
ID Code:3343
Deposited By:Helen Webb
Deposited On:28 Nov 2007
Last Modified:17 Apr 2013 14:27

Repository Staff Only: item control page