DSpace Repository

A comparative study of methods for defect detection in textile fabrics

Show simple item record

dc.contributor.author Nsengiyumva, P.
dc.contributor.author Vermaak, H.
dc.contributor.author Luwes, N.
dc.contributor.other Central University of Technology, Free State, Bloemfontein: Journal for New Generation Sciences
dc.date.accessioned 2016-06-03T14:03:02Z
dc.date.available 2016-06-03T14:03:02Z
dc.date.issued 2015
dc.date.issued 2015
dc.identifier.issn 16844998
dc.identifier.uri http://hdl.handle.net/11462/805
dc.description Published Article en_US
dc.description.abstract Fabric defect detection methods have been broadly classified into three categories; statistical methods, spectral methods and model-based methods. The performance of each method relies on the discriminative ability of texture features it uses. Each of the three categories has its own advantages and disadvantages and some researchers have recommended their combination for improved performance. In this paper, we compare the performance of three fabric defect detection methods, one from each of the three categories. The three methods are based on the grey-level co-occurrence matrices (GLCM), the undecimated discrete wavelet transform (UDWT) and the Gaussian Markov Random field models (GMRF) respectively from the statistical, spectral and model-based categories. The tests were done using the textile images from the TILDA dataset. To ensure classifier independence on the outcome of the comparison, the Euclidean distance and feed forward neural network classifiers were used for defect detection using the features obtained from each of the three methods. The results show that GLCM features allowed better defect detection than wavelet features and that wavelet features allowed better detection than GMRF features. en_US
dc.format.extent 640 763 bytes, 1 file
dc.format.mimetype Application/PDF
dc.language.iso en_US en_US
dc.publisher Central University of Technology, Free State, Bloemfontein: Journal for New Generation Sciences
dc.relation.ispartofseries Journal for New Generation Sciences;Vol 13, Issue 3
dc.subject Grey-level co-occurrence matrix, en_US
dc.subject Wavelet transform en_US
dc.subject Markov random field en_US
dc.subject Euclidean distance classifier en_US
dc.subject Neural networks en_US
dc.title A comparative study of methods for defect detection in textile fabrics en_US
dc.type Article en_US
dc.rights.holder Journal for New Generation Sciences


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Browse

My Account