File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Minimum classification error-based neural network for inspection of fabric defects
Title | Minimum classification error-based neural network for inspection of fabric defects |
---|---|
Authors | |
Keywords | Artificial neural network Fabric defect classification error Wavelet frames |
Issue Date | 2004 |
Citation | Proceedings Of The Iasted International Conference On Neural Networks And Computational Intelligence, 2004, p. 196-200 How to Cite? |
Abstract | This paper presents a new method for fabric defect classification by using wavelet frames based feature extractor and minimum classification error based neural network. Channel variances at the outputs of the wavelet frame decomposition are extracted to characterize each non-overlapping window of the fabric image, which is further assigned to a defect category with a neural network classifier. In our work, Minimum Classification Error (MCE) criterion is used in the training of the neural network for the improvement of classification performance. The developed defect classification method has been evaluated on the classification of 329 defect samples from nine types of defects and 82 nondefect samples, where an 93.4% classification accuracy was achieved. |
Persistent Identifier | http://hdl.handle.net/10722/99057 |
References |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Pang, G | en_HK |
dc.contributor.author | Yang, X | en_HK |
dc.date.accessioned | 2010-09-25T18:14:05Z | - |
dc.date.available | 2010-09-25T18:14:05Z | - |
dc.date.issued | 2004 | en_HK |
dc.identifier.citation | Proceedings Of The Iasted International Conference On Neural Networks And Computational Intelligence, 2004, p. 196-200 | en_HK |
dc.identifier.uri | http://hdl.handle.net/10722/99057 | - |
dc.description.abstract | This paper presents a new method for fabric defect classification by using wavelet frames based feature extractor and minimum classification error based neural network. Channel variances at the outputs of the wavelet frame decomposition are extracted to characterize each non-overlapping window of the fabric image, which is further assigned to a defect category with a neural network classifier. In our work, Minimum Classification Error (MCE) criterion is used in the training of the neural network for the improvement of classification performance. The developed defect classification method has been evaluated on the classification of 329 defect samples from nine types of defects and 82 nondefect samples, where an 93.4% classification accuracy was achieved. | en_HK |
dc.language | eng | en_HK |
dc.relation.ispartof | Proceedings of the IASTED International Conference on Neural Networks and Computational Intelligence | en_HK |
dc.subject | Artificial neural network | en_HK |
dc.subject | Fabric defect classification error | en_HK |
dc.subject | Wavelet frames | en_HK |
dc.title | Minimum classification error-based neural network for inspection of fabric defects | en_HK |
dc.type | Conference_Paper | en_HK |
dc.identifier.email | Pang, G:gpang@eee.hku.hk | en_HK |
dc.identifier.authority | Pang, G=rp00162 | en_HK |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.scopus | eid_2-s2.0-11144275756 | en_HK |
dc.identifier.hkuros | 90396 | en_HK |
dc.relation.references | http://www.scopus.com/mlt/select.url?eid=2-s2.0-11144275756&selection=ref&src=s&origin=recordpage | en_HK |
dc.identifier.spage | 196 | en_HK |
dc.identifier.epage | 200 | en_HK |
dc.identifier.scopusauthorid | Pang, G=7103393283 | en_HK |
dc.identifier.scopusauthorid | Yang, X=7406505132 | en_HK |