File Download
 
Links for fulltext
(May Require Subscription)
 
Supplementary

Conference Paper: Retrieving biomedical images through content-based learning from examples using fine granularity
  • Basic View
  • Metadata View
  • XML View
TitleRetrieving biomedical images through content-based learning from examples using fine granularity
 
AuthorsJiang, H
Xu, S
Lau, FCM
 
Issue Date2012
 
PublisherS P I E - International Society for Optical Engineering. The Journal's web site is located at http://spie.org/x1848.xml?WT.svl=mddp2
 
CitationConference 8319 - Medical Imaging 2012: Advanced PACS-based Imaging Informatics and Therapeutic Applications, San Diego, California, USA, 4 February 2012. In Proceedings of SPIE, 2012, v. 8319, p. article no. 83190M [How to Cite?]
DOI: http://dx.doi.org/10.1117/12.913765
 
AbstractTraditional content-based image retrieval methods based on learning from examples analyze and attempt to understand high-level semantics of an image as a whole. They typically apply certain case-based reasoning technique to interpret and retrieve images through measuring the semantic similarity or relatedness between example images and search candidate images. The drawback of such a traditional content-based image retrieval paradigm is that the summation of imagery contents in an image tends to lead to tremendous variation from image to image. Hence, semantically related images may only exhibit a small pocket of common elements, if at all. Such variability in image visual composition poses great challenges to content-based image retrieval methods that operate at the granularity of entire images. In this study, we explore a new content-based image retrieval algorithm that mines visual patterns of finer granularities inside a whole image to identify visual instances which can more reliably and generically represent a given search concept. We performed preliminary experiments to validate our new idea for content-based image retrieval and obtained very encouraging results.
 
DescriptionSession: Data Mining II
 
ISSN0277-786X
2013 SCImago Journal Rankings: 0.203
 
DOIhttp://dx.doi.org/10.1117/12.913765
 
DC FieldValue
dc.contributor.authorJiang, H
 
dc.contributor.authorXu, S
 
dc.contributor.authorLau, FCM
 
dc.date.accessioned2012-10-18T08:49:50Z
 
dc.date.available2012-10-18T08:49:50Z
 
dc.date.issued2012
 
dc.description.abstractTraditional content-based image retrieval methods based on learning from examples analyze and attempt to understand high-level semantics of an image as a whole. They typically apply certain case-based reasoning technique to interpret and retrieve images through measuring the semantic similarity or relatedness between example images and search candidate images. The drawback of such a traditional content-based image retrieval paradigm is that the summation of imagery contents in an image tends to lead to tremendous variation from image to image. Hence, semantically related images may only exhibit a small pocket of common elements, if at all. Such variability in image visual composition poses great challenges to content-based image retrieval methods that operate at the granularity of entire images. In this study, we explore a new content-based image retrieval algorithm that mines visual patterns of finer granularities inside a whole image to identify visual instances which can more reliably and generically represent a given search concept. We performed preliminary experiments to validate our new idea for content-based image retrieval and obtained very encouraging results.
 
dc.description.naturepublished_or_final_version
 
dc.descriptionSession: Data Mining II
 
dc.identifier.citationConference 8319 - Medical Imaging 2012: Advanced PACS-based Imaging Informatics and Therapeutic Applications, San Diego, California, USA, 4 February 2012. In Proceedings of SPIE, 2012, v. 8319, p. article no. 83190M [How to Cite?]
DOI: http://dx.doi.org/10.1117/12.913765
 
dc.identifier.doihttp://dx.doi.org/10.1117/12.913765
 
dc.identifier.epagearticle no. 83190M
 
dc.identifier.hkuros211543
 
dc.identifier.issn0277-786X
2013 SCImago Journal Rankings: 0.203
 
dc.identifier.spagearticle no. 83190M
 
dc.identifier.urihttp://hdl.handle.net/10722/169311
 
dc.identifier.volume8319
 
dc.languageeng
 
dc.publisherS P I E - International Society for Optical Engineering. The Journal's web site is located at http://spie.org/x1848.xml?WT.svl=mddp2
 
dc.publisher.placeUnited States
 
dc.relation.ispartofProceedings of SPIE - International Society for Optical Engineering
 
dc.rightsProceedings of SPIE - International Society for Optical Engineering. Copyright © S P I E - International Society for Optical Engineering.
 
dc.rightsCopyright notice format: Copyright 2012 Society of Photo-Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.
 
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License
 
dc.titleRetrieving biomedical images through content-based learning from examples using fine granularity
 
dc.typeConference_Paper
 
<?xml encoding="utf-8" version="1.0"?>
<item><contributor.author>Jiang, H</contributor.author>
<contributor.author>Xu, S</contributor.author>
<contributor.author>Lau, FCM</contributor.author>
<date.accessioned>2012-10-18T08:49:50Z</date.accessioned>
<date.available>2012-10-18T08:49:50Z</date.available>
<date.issued>2012</date.issued>
<identifier.citation>Conference 8319 - Medical Imaging 2012: Advanced PACS-based Imaging Informatics and Therapeutic Applications, San Diego, California, USA, 4 February 2012. In Proceedings of SPIE, 2012, v. 8319, p. article no. 83190M</identifier.citation>
<identifier.issn>0277-786X</identifier.issn>
<identifier.uri>http://hdl.handle.net/10722/169311</identifier.uri>
<description>Session: Data Mining II</description>
<description.abstract>Traditional content-based image retrieval methods based on learning from examples analyze and attempt to understand high-level semantics of an image as a whole. They typically apply certain case-based reasoning technique to interpret and retrieve images through measuring the semantic similarity or relatedness between example images and search candidate images. The drawback of such a traditional content-based image retrieval paradigm is that the summation of imagery contents in an image tends to lead to tremendous variation from image to image. Hence, semantically related images may only exhibit a small pocket of common elements, if at all. Such variability in image visual composition poses great challenges to content-based image retrieval methods that operate at the granularity of entire images. In this study, we explore a new content-based image retrieval algorithm that mines visual patterns of finer granularities inside a whole image to identify visual instances which can more reliably and generically represent a given search concept. We performed preliminary experiments to validate our new idea for content-based image retrieval and obtained very encouraging results.</description.abstract>
<language>eng</language>
<publisher>S P I E - International Society for Optical Engineering. The Journal&apos;s web site is located at http://spie.org/x1848.xml?WT.svl=mddp2</publisher>
<relation.ispartof>Proceedings of SPIE - International Society for Optical Engineering</relation.ispartof>
<rights>Proceedings of SPIE - International Society for Optical Engineering. Copyright &#169; S P I E - International Society for Optical Engineering.</rights>
<rights>Copyright notice format: Copyright 2012 Society of Photo-Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.</rights>
<rights>Creative Commons: Attribution 3.0 Hong Kong License</rights>
<title>Retrieving biomedical images through content-based learning from examples using fine granularity</title>
<type>Conference_Paper</type>
<description.nature>published_or_final_version</description.nature>
<identifier.doi>10.1117/12.913765</identifier.doi>
<identifier.hkuros>211543</identifier.hkuros>
<identifier.volume>8319</identifier.volume>
<identifier.spage>article no. 83190M</identifier.spage>
<identifier.epage>article no. 83190M</identifier.epage>
<publisher.place>United States</publisher.place>
<bitstream.url>http://hub.hku.hk/bitstream/10722/169311/1/Content.pdf</bitstream.url>
</item>