File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Scene categorization by introducing contextual information to the visual words

TitleScene categorization by introducing contextual information to the visual words
Authors
KeywordsComputers
Issue Date2009
PublisherSpringer Verlag. The Journal's web site is located at http://springerlink.com/content/105633/
Citation
The 5th Intenational Symposium on Visual Computing (ISVC 2009), Las Vegas, NV., 30 November-2 December 2009. In Lecture Notes in Computer Science, 2009, v. 5875 pt. 1, p. 297-306 How to Cite?
AbstractIn this paper, we propose a novel scene categorization method based on contextual visual words. In this method, we extend the traditional 'bags of visual words' model by introducing contextual information from the coarser scale level and neighbor regions to the local region of interest. The proposed method is evaluated over two scene classification datasets of 6,447 images altogether, with 8 and 13 scene categories respectively using 10-fold cross-validation. The experimental results show that the proposed method achieves 90.30% and 87.63% recognition success for Dataset 1 and 2 respectively, which significantly outperforms previous methods based on the visual words that represent the local information in a statistical manner. Furthermore, the proposed method also outperforms the spatial pyramid matching based scene categorization method, one of the scene categorization methods which achieved the best performance on these two datasets reported in previous literatures. © 2009 Springer-Verlag.
DescriptionLNCS v. 5875 is the conference proceedings of ISVC 2009
Persistent Identifierhttp://hdl.handle.net/10722/126184
ISSN
2005 Impact Factor: 0.402
2015 SCImago Journal Rankings: 0.252
References

 

DC FieldValueLanguage
dc.contributor.authorQin, Jen_HK
dc.contributor.authorYung, NHCen_HK
dc.date.accessioned2010-10-31T12:14:21Z-
dc.date.available2010-10-31T12:14:21Z-
dc.date.issued2009en_HK
dc.identifier.citationThe 5th Intenational Symposium on Visual Computing (ISVC 2009), Las Vegas, NV., 30 November-2 December 2009. In Lecture Notes in Computer Science, 2009, v. 5875 pt. 1, p. 297-306en_HK
dc.identifier.issn0302-9743en_HK
dc.identifier.urihttp://hdl.handle.net/10722/126184-
dc.descriptionLNCS v. 5875 is the conference proceedings of ISVC 2009-
dc.description.abstractIn this paper, we propose a novel scene categorization method based on contextual visual words. In this method, we extend the traditional 'bags of visual words' model by introducing contextual information from the coarser scale level and neighbor regions to the local region of interest. The proposed method is evaluated over two scene classification datasets of 6,447 images altogether, with 8 and 13 scene categories respectively using 10-fold cross-validation. The experimental results show that the proposed method achieves 90.30% and 87.63% recognition success for Dataset 1 and 2 respectively, which significantly outperforms previous methods based on the visual words that represent the local information in a statistical manner. Furthermore, the proposed method also outperforms the spatial pyramid matching based scene categorization method, one of the scene categorization methods which achieved the best performance on these two datasets reported in previous literatures. © 2009 Springer-Verlag.en_HK
dc.languageengen_HK
dc.publisherSpringer Verlag. The Journal's web site is located at http://springerlink.com/content/105633/en_HK
dc.relation.ispartofLecture Notes in Computer Scienceen_HK
dc.rightsThe original publication is available at www.springerlink.com-
dc.subjectComputers-
dc.titleScene categorization by introducing contextual information to the visual wordsen_HK
dc.typeConference_Paperen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=0302-9743&volume=5875&spage=297&epage=306&date=2009&atitle=Scene+categorization+by+introducing+contextual+information+to+the+visual+words-
dc.identifier.emailYung, NHC:nyung@eee.hku.hken_HK
dc.identifier.authorityYung, NHC=rp00226en_HK
dc.description.naturelink_to_OA_fulltext-
dc.identifier.doi10.1007/978-3-642-10331-5_28en_HK
dc.identifier.scopuseid_2-s2.0-72449152988en_HK
dc.identifier.hkuros176248en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-72449152988&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume5875en_HK
dc.identifier.issuept. 1en_HK
dc.identifier.spage297en_HK
dc.identifier.epage306en_HK
dc.publisher.placeGermanyen_HK
dc.description.otherThe 5th Intenational Symposium on Visual Computing (ISVC 2009), Las Vegas, NV., 30 November-2 December 2009. In Lecture Notes in Computer Science, 2009, v. 5875 pt. 1, p. 297-306-
dc.identifier.scopusauthoridQin, J=24450951900en_HK
dc.identifier.scopusauthoridYung, NHC=7003473369en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats