File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Feature matching and deformation for texture synthesis

TitleFeature matching and deformation for texture synthesis
Authors
KeywordsDistance Transforms
Image Registration
Oriented Features
Texture Warping
Issue Date2004
Citation
Acm Transactions On Graphics, 2004, v. 23 n. 3, p. 364-367 How to Cite?
AbstractOne significant problem in patch-based texture synthesis is the presence of broken features at the boundary of adjacent patches. The reason is that optimization schemes for patch merging may fail when neighborhood search cannot find satisfactory candidates in the sample texture because of an inaccurate similarity measure. In this paper, we consider both curvilinear features and their deformation. We develop a novel algorithm to perform feature matching and alignment by measuring structural similarity. Our technique extracts a feature map from the sample texture, and produces both a new feature map and texture map. Texture synthesis guided by feature maps can significantly reduce the number of feature discontinuities and related artifacts, and gives rise to satisfactory results.
Persistent Identifierhttp://hdl.handle.net/10722/151848
ISSN
2015 Impact Factor: 4.218
2015 SCImago Journal Rankings: 2.552
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorWu, Qen_US
dc.contributor.authorYu, Yen_US
dc.date.accessioned2012-06-26T06:30:03Z-
dc.date.available2012-06-26T06:30:03Z-
dc.date.issued2004en_US
dc.identifier.citationAcm Transactions On Graphics, 2004, v. 23 n. 3, p. 364-367en_US
dc.identifier.issn0730-0301en_US
dc.identifier.urihttp://hdl.handle.net/10722/151848-
dc.description.abstractOne significant problem in patch-based texture synthesis is the presence of broken features at the boundary of adjacent patches. The reason is that optimization schemes for patch merging may fail when neighborhood search cannot find satisfactory candidates in the sample texture because of an inaccurate similarity measure. In this paper, we consider both curvilinear features and their deformation. We develop a novel algorithm to perform feature matching and alignment by measuring structural similarity. Our technique extracts a feature map from the sample texture, and produces both a new feature map and texture map. Texture synthesis guided by feature maps can significantly reduce the number of feature discontinuities and related artifacts, and gives rise to satisfactory results.en_US
dc.languageengen_US
dc.relation.ispartofACM Transactions on Graphicsen_US
dc.subjectDistance Transformsen_US
dc.subjectImage Registrationen_US
dc.subjectOriented Featuresen_US
dc.subjectTexture Warpingen_US
dc.titleFeature matching and deformation for texture synthesisen_US
dc.typeConference_Paperen_US
dc.identifier.emailYu, Y:yzyu@cs.hku.hken_US
dc.identifier.authorityYu, Y=rp01415en_US
dc.description.naturelink_to_subscribed_fulltexten_US
dc.identifier.doi10.1145/1015706.1015730en_US
dc.identifier.scopuseid_2-s2.0-12844254289en_US
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-12844254289&selection=ref&src=s&origin=recordpageen_US
dc.identifier.volume23en_US
dc.identifier.issue3en_US
dc.identifier.spage364en_US
dc.identifier.epage367en_US
dc.identifier.isiWOS:000222972600023-
dc.publisher.placeUnited Statesen_US
dc.identifier.scopusauthoridWu, Q=51964899100en_US
dc.identifier.scopusauthoridYu, Y=8554163500en_US
dc.identifier.citeulike3823959-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats