File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Scene categorization with multi-scale category-specific visual words

TitleScene categorization with multi-scale category-specific visual words
Authors
KeywordsCategory-specific
Multi-scale
Scene categorization
Visual words
Issue Date2009
PublisherSPIE - International Society for Optical Engineering. The Journal's web site is located at http://spie.org/x1848.xml
Citation
Proceedings Of SPIE - The International Society For Optical Engineering, 2009, v. 7252, article no. 72520N How to Cite?
AbstractIn this paper, we propose a scene categorization method based on multi-scale category-specific visual words. The proposed method quantizes visual words in a multi-scale manner which combines the global-feature-based and local-feature-based scene categorization approaches into a uniform framework. Unlike traditional visual word creation methods which quantize visual words from the whole training images without considering their categories, we form visual words from the training images grouped in different categories then collate the visual words from different categories to form the final codebook. This category-specific strategy provides us with more discriminative visual words for scene categorization. Based on the codebook, we compile a feature vector that encodes the presence of different visual words to represent a given image. A SVM classifier with linear kernel is then employed to select the features and classify the images. The proposed method is evaluated over two scene classification datasets of 6,447 images altogether using 10-fold cross-validation. The results show that the classification accuracy has been improved significantly comparing with the methods using the traditional visual words. And the proposed method is comparable to the best results published in the previous literatures in terms of classification accuracy rate and has the advantage in terms of simplicity. © 2009 SPIE-IS&T.
DescriptionIS&T/SPIE Conference on Intelligent Robots and Computer Vision XXVI: Algorithms and Techniques
Persistent Identifierhttp://hdl.handle.net/10722/62064
ISSN
2023 SCImago Journal Rankings: 0.152
References

 

DC FieldValueLanguage
dc.contributor.authorQin, Jen_HK
dc.contributor.authorYung, NHCen_HK
dc.date.accessioned2010-07-13T03:53:09Z-
dc.date.available2010-07-13T03:53:09Z-
dc.date.issued2009en_HK
dc.identifier.citationProceedings Of SPIE - The International Society For Optical Engineering, 2009, v. 7252, article no. 72520Nen_HK
dc.identifier.issn0277-786Xen_HK
dc.identifier.urihttp://hdl.handle.net/10722/62064-
dc.descriptionIS&T/SPIE Conference on Intelligent Robots and Computer Vision XXVI: Algorithms and Techniquesen_HK
dc.description.abstractIn this paper, we propose a scene categorization method based on multi-scale category-specific visual words. The proposed method quantizes visual words in a multi-scale manner which combines the global-feature-based and local-feature-based scene categorization approaches into a uniform framework. Unlike traditional visual word creation methods which quantize visual words from the whole training images without considering their categories, we form visual words from the training images grouped in different categories then collate the visual words from different categories to form the final codebook. This category-specific strategy provides us with more discriminative visual words for scene categorization. Based on the codebook, we compile a feature vector that encodes the presence of different visual words to represent a given image. A SVM classifier with linear kernel is then employed to select the features and classify the images. The proposed method is evaluated over two scene classification datasets of 6,447 images altogether using 10-fold cross-validation. The results show that the classification accuracy has been improved significantly comparing with the methods using the traditional visual words. And the proposed method is comparable to the best results published in the previous literatures in terms of classification accuracy rate and has the advantage in terms of simplicity. © 2009 SPIE-IS&T.en_HK
dc.languageengen_HK
dc.publisherSPIE - International Society for Optical Engineering. The Journal's web site is located at http://spie.org/x1848.xmlen_HK
dc.relation.ispartofProceedings of SPIE - The International Society for Optical Engineeringen_HK
dc.rightsCopyright 2009 Society of Photo‑Optical Instrumentation Engineers (SPIE). One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this publication for a fee or for commercial purposes, and modification of the contents of the publication are prohibited. This article is available online at https://doi.org/10.1117/12.805850-
dc.subjectCategory-specificen_HK
dc.subjectMulti-scaleen_HK
dc.subjectScene categorizationen_HK
dc.subjectVisual wordsen_HK
dc.titleScene categorization with multi-scale category-specific visual wordsen_HK
dc.typeConference_Paperen_HK
dc.identifier.emailYung, NHC:nyung@eee.hku.hken_HK
dc.identifier.authorityYung, NHC=rp00226en_HK
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1117/12.805850en_HK
dc.identifier.scopuseid_2-s2.0-63549108762en_HK
dc.identifier.hkuros164710en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-63549108762&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume7252en_HK
dc.publisher.placeUnited Statesen_HK
dc.identifier.scopusauthoridQin, J=24450951900en_HK
dc.identifier.scopusauthoridYung, NHC=7003473369en_HK
dc.identifier.issnl0277-786X-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats