File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Motif-based defect detection for patterned fabric

TitleMotif-based defect detection for patterned fabric
Authors
KeywordsDefect detection
Lattice
Motif
Patterned fabric
Texture analysis
Wallpaper group
Issue Date2008
PublisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/pr
Citation
Pattern Recognition, 2008, v. 41 n. 6, p. 1878-1894 How to Cite?
AbstractThis paper proposes a generalized motif-based method for detecting defects in 16 out of 17 wallpaper groups in 2D patterned texture. It assumes that most patterned texture can be decomposed into lattices and their constituents-motifs. It then utilizes the symmetry property of motifs to calculate the energy of moving subtraction and its variance among different motifs. By learning the distribution of these values over a number of defect-free patterns, boundary conditions for discerning defective and defect-free patterns can be determined. This paper presents the theoretical foundation of the method, and defines the relations between motifs and lattice, from which a new concept called energy of moving subtraction is derived using norm metric measurement between a collection of circular shift matrices of motif and itself. It has been shown in this paper that the energy of moving subtraction amplifies the defect information of the defective motif. Together with its variance, an energy-variance space is further defined where decision boundaries are drawn for classifying defective and defect-free motifs. As the 16 wallpaper groups of patterned fabric can be transformed into three major groups, the proposed method is evaluated over these three major groups, from which 160 defect-free lattices samples are used for defining the decision boundaries, with 140 defect-free and 113 defective samples used for testing. An overall detection success rate of 93.32% is achieved for the proposed method. No other generalized approach can achieve this success rate has been reported before, and hence this result outperforms all other previously published approaches. © 2007 Elsevier Ltd. All rights reserved.
Persistent Identifierhttp://hdl.handle.net/10722/73614
ISSN
2015 Impact Factor: 3.399
2015 SCImago Journal Rankings: 2.051
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorNgan, HYTen_HK
dc.contributor.authorPang, GKHen_HK
dc.contributor.authorYung, NHCen_HK
dc.date.accessioned2010-09-06T06:53:05Z-
dc.date.available2010-09-06T06:53:05Z-
dc.date.issued2008en_HK
dc.identifier.citationPattern Recognition, 2008, v. 41 n. 6, p. 1878-1894en_HK
dc.identifier.issn0031-3203en_HK
dc.identifier.urihttp://hdl.handle.net/10722/73614-
dc.description.abstractThis paper proposes a generalized motif-based method for detecting defects in 16 out of 17 wallpaper groups in 2D patterned texture. It assumes that most patterned texture can be decomposed into lattices and their constituents-motifs. It then utilizes the symmetry property of motifs to calculate the energy of moving subtraction and its variance among different motifs. By learning the distribution of these values over a number of defect-free patterns, boundary conditions for discerning defective and defect-free patterns can be determined. This paper presents the theoretical foundation of the method, and defines the relations between motifs and lattice, from which a new concept called energy of moving subtraction is derived using norm metric measurement between a collection of circular shift matrices of motif and itself. It has been shown in this paper that the energy of moving subtraction amplifies the defect information of the defective motif. Together with its variance, an energy-variance space is further defined where decision boundaries are drawn for classifying defective and defect-free motifs. As the 16 wallpaper groups of patterned fabric can be transformed into three major groups, the proposed method is evaluated over these three major groups, from which 160 defect-free lattices samples are used for defining the decision boundaries, with 140 defect-free and 113 defective samples used for testing. An overall detection success rate of 93.32% is achieved for the proposed method. No other generalized approach can achieve this success rate has been reported before, and hence this result outperforms all other previously published approaches. © 2007 Elsevier Ltd. All rights reserved.en_HK
dc.languageengen_HK
dc.publisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/pren_HK
dc.relation.ispartofPattern Recognitionen_HK
dc.subjectDefect detectionen_HK
dc.subjectLatticeen_HK
dc.subjectMotifen_HK
dc.subjectPatterned fabricen_HK
dc.subjectTexture analysisen_HK
dc.subjectWallpaper groupen_HK
dc.titleMotif-based defect detection for patterned fabricen_HK
dc.typeArticleen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=0031-3203&volume=41 &issue=6&spage=1878&epage=1894&date=2007&atitle=Motif-based+Defect+Detection+for+Patterned+Fabricen_HK
dc.identifier.emailPang, GKH:gpang@eee.hku.hken_HK
dc.identifier.emailYung, NHC:nyung@eee.hku.hken_HK
dc.identifier.authorityPang, GKH=rp00162en_HK
dc.identifier.authorityYung, NHC=rp00226en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.patcog.2007.11.014en_HK
dc.identifier.scopuseid_2-s2.0-38949156800en_HK
dc.identifier.hkuros139396en_HK
dc.identifier.hkuros172006-
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-38949156800&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume41en_HK
dc.identifier.issue6en_HK
dc.identifier.spage1878en_HK
dc.identifier.epage1894en_HK
dc.identifier.eissn1873-5142-
dc.identifier.isiWOS:000254106900003-
dc.publisher.placeNetherlandsen_HK
dc.identifier.scopusauthoridNgan, HYT=7102173824en_HK
dc.identifier.scopusauthoridPang, GKH=7103393283en_HK
dc.identifier.scopusauthoridYung, NHC=7003473369en_HK
dc.identifier.citeulike6019026-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats