Giving order to image queries
Giving order to image queries
Users of image retrieval systems often find it frustrating that the image they are looking for is not ranked near the top of the results they are presented. This paper presents a computational approach for ranking keyworded images in order of relevance to a given keyword. Our approach uses machine learning to attempt to learn what visual features within an image are most related to the keywords, and then provide ranking based on similarity to a visual aggregate. To evaluate the technique, a Web 2.0 application has been developed to obtain a corpus of user-generated ranking information for a given image collection that can be used to evaluate the performance of the ranking algorithm.
Image retrieval, ranking, visual features, web 2.0
9780819469922
682005-1
Hare, Jonathan
65ba2cda-eaaf-4767-a325-cd845504e5a9
Sinclair, Patrick
255443f0-174e-470e-b1d6-97947aad44a9
Lewis, Paul
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
Martinez, Kirk
5f711898-20fc-410e-a007-837d8c57cb18
Gevers, Theo
28d2349c-a752-4d22-9aa5-3580dfc640ca
Jain, Ramesh
44db92e2-0909-47c9-bc34-0ae786c9ab0f
Santini, Simone
9ff9323a-085f-43dd-a0a4-10c0ae88d828
30 January 2008
Hare, Jonathan
65ba2cda-eaaf-4767-a325-cd845504e5a9
Sinclair, Patrick
255443f0-174e-470e-b1d6-97947aad44a9
Lewis, Paul
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
Martinez, Kirk
5f711898-20fc-410e-a007-837d8c57cb18
Gevers, Theo
28d2349c-a752-4d22-9aa5-3580dfc640ca
Jain, Ramesh
44db92e2-0909-47c9-bc34-0ae786c9ab0f
Santini, Simone
9ff9323a-085f-43dd-a0a4-10c0ae88d828
Hare, Jonathan, Sinclair, Patrick, Lewis, Paul and Martinez, Kirk
(2008)
Giving order to image queries.
Gevers, Theo, Jain, Ramesh and Santini, Simone
(eds.)
Multimedia Content Access: Algorithms and Systems II, San Jose, California, United States.
30 - 31 Jan 2008.
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
Users of image retrieval systems often find it frustrating that the image they are looking for is not ranked near the top of the results they are presented. This paper presents a computational approach for ranking keyworded images in order of relevance to a given keyword. Our approach uses machine learning to attempt to learn what visual features within an image are most related to the keywords, and then provide ranking based on similarity to a visual aggregate. To evaluate the technique, a Web 2.0 application has been developed to obtain a corpus of user-generated ranking information for a given image collection that can be used to evaluate the performance of the ranking algorithm.
More information
Published date: 30 January 2008
Additional Information:
Event Dates: 30-31 January 2008
Venue - Dates:
Multimedia Content Access: Algorithms and Systems II, San Jose, California, United States, 2008-01-30 - 2008-01-31
Keywords:
Image retrieval, ranking, visual features, web 2.0
Organisations:
Web & Internet Science
Identifiers
Local EPrints ID: 265187
URI: http://eprints.soton.ac.uk/id/eprint/265187
ISBN: 9780819469922
PURE UUID: 7600be5e-1f08-4121-b56b-fdefd3f1a68f
Catalogue record
Date deposited: 21 Feb 2008 12:15
Last modified: 15 Mar 2024 03:25
Export record
Contributors
Author:
Jonathan Hare
Author:
Patrick Sinclair
Author:
Paul Lewis
Author:
Kirk Martinez
Editor:
Theo Gevers
Editor:
Ramesh Jain
Editor:
Simone Santini
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics