Salient Regions for Query by Image Content
Salient Regions for Query by Image Content
Much previous work on image retrieval has used global features such as colour and texture to describe the content of the image. However, these global features are insufficient to accurately describe the image content when different parts of the image have different characteristics. This paper discusses how this problem can be circumvented by using salient interest points and compares and contrasts an extension to previous work in which the concept of scale is incorporated into the selection of salient regions to select the areas of the image that are most interesting and generate local descriptors to describe the image characteristics in that region. The paper describes and contrasts two such salient region descriptors and compares them through their repeatability rate under a range of common image transforms. Finally, the paper goes on to investigate the performance of one of the salient region detectors in an image retrieval situation.
Computer Vision, Content-based Image Retrieval, Salient Regions
317-325
Hare, Jonathon S.
65ba2cda-eaaf-4767-a325-cd845504e5a9
Lewis, Paul H.
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
Enser, Peter
753fcee9-fd09-4edb-8664-22e5fe5292b3
Kompatsiaris, Yiannis
364cc081-661c-4f71-b6e0-025b02c25592
O'Connor, Noel E.
85878a58-0fe1-4025-bf43-3bcb3960322e
July 2004
Hare, Jonathon S.
65ba2cda-eaaf-4767-a325-cd845504e5a9
Lewis, Paul H.
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
Enser, Peter
753fcee9-fd09-4edb-8664-22e5fe5292b3
Kompatsiaris, Yiannis
364cc081-661c-4f71-b6e0-025b02c25592
O'Connor, Noel E.
85878a58-0fe1-4025-bf43-3bcb3960322e
Hare, Jonathon S. and Lewis, Paul H.
,
Enser, Peter, Kompatsiaris, Yiannis and O'Connor, Noel E.
(eds.)
(2004)
Salient Regions for Query by Image Content.
Lecture Notes in Computer Science, 3115 /, .
Abstract
Much previous work on image retrieval has used global features such as colour and texture to describe the content of the image. However, these global features are insufficient to accurately describe the image content when different parts of the image have different characteristics. This paper discusses how this problem can be circumvented by using salient interest points and compares and contrasts an extension to previous work in which the concept of scale is incorporated into the selection of salient regions to select the areas of the image that are most interesting and generate local descriptors to describe the image characteristics in that region. The paper describes and contrasts two such salient region descriptors and compares them through their repeatability rate under a range of common image transforms. Finally, the paper goes on to investigate the performance of one of the salient region detectors in an image retrieval situation.
More information
Published date: July 2004
Keywords:
Computer Vision, Content-based Image Retrieval, Salient Regions
Organisations:
Web & Internet Science
Identifiers
Local EPrints ID: 259336
URI: http://eprints.soton.ac.uk/id/eprint/259336
ISSN: 0302-9743
PURE UUID: 7eff1c59-dbc5-4e7a-a031-20ef7ff2198c
Catalogue record
Date deposited: 19 Jul 2004
Last modified: 15 Mar 2024 03:25
Export record
Contributors
Author:
Jonathon S. Hare
Author:
Paul H. Lewis
Editor:
Peter Enser
Editor:
Yiannis Kompatsiaris
Editor:
Noel E. O'Connor
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