File Download
 
Links for fulltext
(May Require Subscription)
 
Supplementary

Conference Paper: Image segmentation towards natural clusters
  • Basic View
  • Metadata View
  • XML View
TitleImage segmentation towards natural clusters
 
AuthorsTan, Z1
Yung, NHC1
 
Issue Date2008
 
PublisherIAPR.
 
CitationProceedings - International Conference On Pattern Recognition, 2008 [How to Cite?]
 
AbstractTo find how many clusters in a sample set is an old yet unsolved problem in unsupervised clustering. Many segmentation methods require the user to specify the number of regions in the image or some delicate thresholds to get a sensible segmentation. In this paper, we propose a segmentation method that is able to automatically determine the number of regions in an image. The method effectively discerns distinct regions by analyzing the properties of the joint boundary between neighboring regions. By requiring that every region should be distinct from each other, it is able to choose a natural partition from the partition set which contains all possible partitions. Results are given at the end of this paper to demonstrate the effectiveness of this approach. © 2008 IEEE.
 
DescriptionIntenational Conference on Pattern Recognition
 
ISSN1051-4651
2012 SCImago Journal Rankings: 0.484
 
ReferencesReferences in Scopus
 
DC FieldValue
dc.contributor.authorTan, Z
 
dc.contributor.authorYung, NHC
 
dc.date.accessioned2010-07-13T03:54:49Z
 
dc.date.available2010-07-13T03:54:49Z
 
dc.date.issued2008
 
dc.description.abstractTo find how many clusters in a sample set is an old yet unsolved problem in unsupervised clustering. Many segmentation methods require the user to specify the number of regions in the image or some delicate thresholds to get a sensible segmentation. In this paper, we propose a segmentation method that is able to automatically determine the number of regions in an image. The method effectively discerns distinct regions by analyzing the properties of the joint boundary between neighboring regions. By requiring that every region should be distinct from each other, it is able to choose a natural partition from the partition set which contains all possible partitions. Results are given at the end of this paper to demonstrate the effectiveness of this approach. © 2008 IEEE.
 
dc.description.natureLink_to_subscribed_fulltext
 
dc.descriptionIntenational Conference on Pattern Recognition
 
dc.identifier.citationProceedings - International Conference On Pattern Recognition, 2008 [How to Cite?]
 
dc.identifier.hkuros164706
 
dc.identifier.issn1051-4651
2012 SCImago Journal Rankings: 0.484
 
dc.identifier.scopuseid_2-s2.0-77957934683
 
dc.identifier.urihttp://hdl.handle.net/10722/62146
 
dc.languageeng
 
dc.publisherIAPR.
 
dc.publisher.placeUnited States
 
dc.relation.ispartofProceedings - International Conference on Pattern Recognition
 
dc.relation.referencesReferences in Scopus
 
dc.titleImage segmentation towards natural clusters
 
dc.typeConference_Paper
 
<?xml encoding="utf-8" version="1.0"?>
<item><contributor.author>Tan, Z</contributor.author>
<contributor.author>Yung, NHC</contributor.author>
<date.accessioned>2010-07-13T03:54:49Z</date.accessioned>
<date.available>2010-07-13T03:54:49Z</date.available>
<date.issued>2008</date.issued>
<identifier.citation>Proceedings - International Conference On Pattern Recognition, 2008</identifier.citation>
<identifier.issn>1051-4651</identifier.issn>
<identifier.uri>http://hdl.handle.net/10722/62146</identifier.uri>
<description>Intenational Conference on Pattern Recognition</description>
<description.abstract>To find how many clusters in a sample set is an old yet unsolved problem in unsupervised clustering. Many segmentation methods require the user to specify the number of regions in the image or some delicate thresholds to get a sensible segmentation. In this paper, we propose a segmentation method that is able to automatically determine the number of regions in an image. The method effectively discerns distinct regions by analyzing the properties of the joint boundary between neighboring regions. By requiring that every region should be distinct from each other, it is able to choose a natural partition from the partition set which contains all possible partitions. Results are given at the end of this paper to demonstrate the effectiveness of this approach. &#169; 2008 IEEE.</description.abstract>
<language>eng</language>
<publisher>IAPR.</publisher>
<relation.ispartof>Proceedings - International Conference on Pattern Recognition</relation.ispartof>
<title>Image segmentation towards natural clusters</title>
<type>Conference_Paper</type>
<description.nature>Link_to_subscribed_fulltext</description.nature>
<identifier.scopus>eid_2-s2.0-77957934683</identifier.scopus>
<identifier.hkuros>164706</identifier.hkuros>
<relation.references>http://www.scopus.com/mlt/select.url?eid=2-s2.0-77957934683&amp;selection=ref&amp;src=s&amp;origin=recordpage</relation.references>
<publisher.place>United States</publisher.place>
</item>
Author Affiliations
  1. The University of Hong Kong