Query by low-quality image
Query by low-quality image
The motivation for research on low-quality images comes from a requirement by some museums to respond to queries for pictorial information, submitted in the form of fax messages or other low-quality monochrome images of works of art. The museums have databases of high-resolution images of their artefact collections and the person submitting the query is asking typically whether the museum holds the artwork shown or perhaps some similar work. Often the query image will have no associated metadata and will be produced from a low-resolution picture of the original artwork. The resulting poor quality image, received by the museum, leads to very poor retrieval accuracy when the fax is used in standard query by example searches using, for example, colour, spatial colour or texture matching algorithms. We propose a special retrieval algorithm in order to improve the retrieval accuracy in query by low-quality image application and evaluate it in comparison with more conventional algorithms. Throughout this paper, fax images will be used as the main source of low-quality image for query by low-quality image experiments. Nonetheless, some other forms of low-quality image will also be considered.
content-based image retrieval, low-quality image analysis, wavelet transform
713-724
Fauzi, Mohammad Faizal Ahmad
7dc639ab-36b7-4317-85f4-52449a29be34
Lewis, Paul H.
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
4 May 2009
Fauzi, Mohammad Faizal Ahmad
7dc639ab-36b7-4317-85f4-52449a29be34
Lewis, Paul H.
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
Abstract
The motivation for research on low-quality images comes from a requirement by some museums to respond to queries for pictorial information, submitted in the form of fax messages or other low-quality monochrome images of works of art. The museums have databases of high-resolution images of their artefact collections and the person submitting the query is asking typically whether the museum holds the artwork shown or perhaps some similar work. Often the query image will have no associated metadata and will be produced from a low-resolution picture of the original artwork. The resulting poor quality image, received by the museum, leads to very poor retrieval accuracy when the fax is used in standard query by example searches using, for example, colour, spatial colour or texture matching algorithms. We propose a special retrieval algorithm in order to improve the retrieval accuracy in query by low-quality image application and evaluate it in comparison with more conventional algorithms. Throughout this paper, fax images will be used as the main source of low-quality image for query by low-quality image experiments. Nonetheless, some other forms of low-quality image will also be considered.
Text
Query_by_Low_Quality_Image.pdf
- Other
More information
Published date: 4 May 2009
Keywords:
content-based image retrieval, low-quality image analysis, wavelet transform
Organisations:
Web & Internet Science
Identifiers
Local EPrints ID: 267645
URI: http://eprints.soton.ac.uk/id/eprint/267645
ISSN: 0262-8856
PURE UUID: 58a5a007-8429-4f72-a827-6142ff6df952
Catalogue record
Date deposited: 01 Jul 2009 14:50
Last modified: 14 Mar 2024 08:55
Export record
Altmetrics
Contributors
Author:
Mohammad Faizal Ahmad Fauzi
Author:
Paul H. Lewis
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