File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Robust fabric defect detection and classification using multiple adaptive wavelets

TitleRobust fabric defect detection and classification using multiple adaptive wavelets
Authors
Issue Date2005
PublisherIEE.
Citation
Iee Proceedings: Vision, Image And Signal Processing, 2005, v. 152 n. 6, p. 715-723 How to Cite?
AbstractThe wavelet transform has been widely used for defect detection and classification in fabric images. The detection and classification performance of the wavelet transform approach is closely related to the selection of the wavelet. Instead of predetermining a wavelet, a method of designing a wavelet adapting to the detection or classification of the fabric defects has been developed. For further improvement of the performance, this paper extends the adaptive wavelet-based methodology from the use of a single adaptive wavelet to multiple adaptive wavelets. For each class of fabric defect, a defect-specific adaptive wavelet was designed to enhance the defect region at one channel of the wavelet transform, where the defect region can be detected by using a simple threshold classifier. Corresponding to the multiple defect-specific adaptive wavelets, the multiscale edge responses to defect regions have been shown to be more efficient in characterising the defects, which leads to a new approach to the classification of defects. In comparison with the single adaptive wavelet approach, the use of multiple adaptive wavelets yields better performance on defect detection and classification, especially for defects that are poorly detected by the single adaptive wavelet approach. The proposed method using multiple adaptive wavelets has been evaluated on the inspection of 56 images containing eight classes of fabric defects, and 64 images without defects, where 98.2% detection rate and 1.5% false alarm rate were achieved in defect detection, and 97.5% classification accuracy was achieved in defect classification.
Persistent Identifierhttp://hdl.handle.net/10722/73997
ISSN
2006 Impact Factor: 0.461
2009 SCImago Journal Rankings: 0.450
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorYang, Xen_HK
dc.contributor.authorPang, Gen_HK
dc.contributor.authorYung, Nen_HK
dc.date.accessioned2010-09-06T06:56:48Z-
dc.date.available2010-09-06T06:56:48Z-
dc.date.issued2005en_HK
dc.identifier.citationIee Proceedings: Vision, Image And Signal Processing, 2005, v. 152 n. 6, p. 715-723en_HK
dc.identifier.issn1350-245Xen_HK
dc.identifier.urihttp://hdl.handle.net/10722/73997-
dc.description.abstractThe wavelet transform has been widely used for defect detection and classification in fabric images. The detection and classification performance of the wavelet transform approach is closely related to the selection of the wavelet. Instead of predetermining a wavelet, a method of designing a wavelet adapting to the detection or classification of the fabric defects has been developed. For further improvement of the performance, this paper extends the adaptive wavelet-based methodology from the use of a single adaptive wavelet to multiple adaptive wavelets. For each class of fabric defect, a defect-specific adaptive wavelet was designed to enhance the defect region at one channel of the wavelet transform, where the defect region can be detected by using a simple threshold classifier. Corresponding to the multiple defect-specific adaptive wavelets, the multiscale edge responses to defect regions have been shown to be more efficient in characterising the defects, which leads to a new approach to the classification of defects. In comparison with the single adaptive wavelet approach, the use of multiple adaptive wavelets yields better performance on defect detection and classification, especially for defects that are poorly detected by the single adaptive wavelet approach. The proposed method using multiple adaptive wavelets has been evaluated on the inspection of 56 images containing eight classes of fabric defects, and 64 images without defects, where 98.2% detection rate and 1.5% false alarm rate were achieved in defect detection, and 97.5% classification accuracy was achieved in defect classification.en_HK
dc.languageengen_HK
dc.publisherIEE.en_HK
dc.relation.ispartofIEE Proceedings: Vision, Image and Signal Processingen_HK
dc.titleRobust fabric defect detection and classification using multiple adaptive waveletsen_HK
dc.typeConference_Paperen_HK
dc.identifier.emailPang, G:gpang@eee.hku.hken_HK
dc.identifier.emailYung, N:nyung@eee.hku.hken_HK
dc.identifier.authorityPang, G=rp00162en_HK
dc.identifier.authorityYung, N=rp00226en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1049/ip-vis:20045131en_HK
dc.identifier.scopuseid_2-s2.0-29144497884en_HK
dc.identifier.hkuros122311en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-29144497884&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume152en_HK
dc.identifier.issue6en_HK
dc.identifier.spage715en_HK
dc.identifier.epage723en_HK
dc.identifier.isiWOS:000234308000007-
dc.publisher.placeUnited Statesen_HK
dc.identifier.scopusauthoridYang, X=7406505132en_HK
dc.identifier.scopusauthoridPang, G=7103393283en_HK
dc.identifier.scopusauthoridYung, N=7003473369en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats