To read this content please select one of the options below:

Detecting Defects in Weft-knitted Fabrics Using Texture-Recognition Methods

S. Shaikhzadeh Najar (Dept. of Textile Engineering, Amirkabir University of Technology, Tehran, Iran.)
R. Ghazi Saeidi (2Dept. of Textiles, Science and Research Campus of Azad University, Tehran, Iran.)
M. Latifi (Dept. of Textile Engineering, Amirkabir University of Technology, Tehran, Iran.)
A.Ghazi Saeidi (Electronic Engineering Dept., Mazandaran University, Babol, Iran.)
A.H. Rezaei (Dept. of Electrical Engineering, Amirkabir University of Technology, Tehran, Iran.)

Research Journal of Textile and Apparel

ISSN: 1560-6074

Article publication date: 1 May 2004

44

Abstract

This paper describes fabric inspection system aided by computer vision to detect and classify defects in circular knitted fabrics using different common texture-recognition methods, including co-occurrence matrices, the discrete Fourier transform, wavelets, Gabor, and clustering. The images of the fabrics were broadly classified into six classes: cracks, holes, vertical stripes, horizontal stripes, soil freckles, and defect-free. One hundred and twenty images (256 gray level and 100 dpi) containing 20 images of defect-free fabrics (rib 1x1) as well as 100 images corresponding to five different categories were used. In general, one-half of the images in each category were employed for training and the remaining images were used for testing.

The application of the clustering method applied in this work was found to be highly promising at identifying defects in knitted fabrics. With an overall success rate of 91.6%, the clustering method has a higher efficiency value than all of the other methods. In the case of the wavelet and Gabor methods, the results are acceptable. However, the overall success rates of the co-occurrence matrix and Fourier transform methods in recognizing defects in knitted fabrics are not acceptable.

Keywords

Citation

Najar, S.S., Saeidi, R.G., Latifi, M., Saeidi, A.G. and Rezaei, A.H. (2004), "Detecting Defects in Weft-knitted Fabrics Using Texture-Recognition Methods", Research Journal of Textile and Apparel, Vol. 8 No. 2, pp. 12-20. https://doi.org/10.1108/RJTA-08-02-2004-B002

Publisher

:

Emerald Group Publishing Limited

Copyright © 2004 Emerald Group Publishing Limited

Related articles