Full metadata record
DC FieldValueLanguage
dc.contributor.authorHotta, Kazuhiro
dc.contributor.editorBaranoski, Gladimir
dc.contributor.editorSkala, Václav
dc.date.accessioned2014-03-18T09:33:11Z
dc.date.available2014-03-18T09:33:11Z
dc.date.issued2011
dc.identifier.citationWSCG '2011: Communication Papers Proceedings: The 19th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 91-98.en
dc.identifier.isbn978-80-86943-82-4
dc.identifier.urihttp://wscg.zcu.cz/WSCG2011/!_2011_WSCG-Short_Papers.pdf
dc.identifier.urihttp://hdl.handle.net/11025/10826
dc.description.abstractThis paper presents a scene classification method using the integration of the reconstruction errors by local Kernel Principal Component Analysis (KPCA) and global KPCA. There are some methods for integrating local and global features. However, it is important to give obvious different role to each feature. In the proposed method, global feature with topological information represents the rough composition of scenes and local feature without position information represents fine part of scenes. Experimental results show that accuracy is improved by using the reconstruction errors obtained from the different point of views. The proposed method is much better than only local KPCA, global KPCA and linear Support Vector Machine (SVM) of bag-of-visual words with the same basic feature. Our method is also comparable to conventional methods using the same database.en
dc.format8 s.cs
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.publisherVáclav Skala - UNION Agencycs
dc.relation.ispartofseriesWSCG '2011: Communication Papers Proceedingsen
dc.rights© Václav Skala - UNION Agencycs
dc.subjectklasifikace scénycs
dc.subjectkernelová analýza hlavních komponentcs
dc.titleIntegration of Reconstruction Error Obtained by Local and Global Kernel PCA with Different Roleen
dc.typekonferenční příspěvekcs
dc.typeconferenceObjecten
dc.rights.accessopenAccessen
dc.type.versionpublishedVersionen
dc.subject.translatedkernel principal component analysisen
dc.subject.translatedscene classificationen
dc.type.statusPeer-revieweden
dc.type.driverinfo:eu-repo/semantics/conferenceObjecten
dc.type.driverinfo:eu-repo/semantics/publishedVersionen
Appears in Collections:WSCG '2011: Communication Papers Proceedings

Files in This Item:
File Description SizeFormat 
Hotta.pdfPlný text542,75 kBAdobe PDFView/Open


Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/10826

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.