Task-based image annotation and retrieval

Dympna O'Sullivan, David Wilson, Michela Bertolotto, Eoin McLoughlin

Research output: Chapter in Book/Published conference outputConference publication

Abstract

In order to address problems of information overload in digital imagery task domains we have developed an interactive approach to the capture and reuse of image context information. Our framework models different aspects of the relationship between images and domain tasks they support by monitoring the interactive manipulation and annotation of task-relevant imagery. The approach allows us to gauge a measure of a user's intentions as they complete goal-directed image tasks. As users analyze retrieved imagery their interactions are captured and an expert task context is dynamically constructed. This human expertise, proficiency, and knowledge can then be leveraged to support other users in carrying out similar domain tasks. We have applied our techniques to two multimedia retrieval applications for two different image domains, namely the geo-spatial and medical imagery domains.
Original languageEnglish
Title of host publicationRough sets, fuzzy sets, data mining and granular computing
Subtitle of host publication11th International Conference, RSFDGrC 2007, Toronto, Canada, May 14-16, 2007. Proceedings
EditorsAijun An, Jerzy Stefanowski, Sheela Ramanna, Cory J. Butz, Witold Pedrycz, Guoyin Wang
Place of PublicationBerlin (DE)
PublisherSpringer
Pages451-458
Number of pages8
ISBN (Electronic)978-3-540-72530-5
ISBN (Print)978-3-540-72529-9
DOIs
Publication statusPublished - 2007
Event11th International Conference, RSFDGrC 2007 - Toronto, Canada
Duration: 14 May 200716 May 2007

Publication series

NameLecture notes in computer science
PublisherSpringer
Volume4482
ISSN (Print)0302-9743

Conference

Conference11th International Conference, RSFDGrC 2007
Country/TerritoryCanada
CityToronto
Period14/05/0716/05/07

Fingerprint

Dive into the research topics of 'Task-based image annotation and retrieval'. Together they form a unique fingerprint.

Cite this