Start Submission Become a Reviewer

Reading: Defect Detection in Woven Fabrics by Analysis of Co-occurrence Texture Features as a Functio...

Download

A- A+
Alt. Display

Section I

Defect Detection in Woven Fabrics by Analysis of Co-occurrence Texture Features as a Function of Gray-level Quantization and Window Size

Authors:

P. S. H. Pallemulla ,

University of Moratuwa, LK
About P. S. H.

Research Assistant

 

AMIE(SL), B.Sc. Eng. Hons (KDU)

X close

S. J. Sooriyaarachchi,

University of Moratuwa, LK
About S. J.

Senior Lecturer in Computer Science and Engineering

 

AMIE(SL), MCS(SL), AMTILP, B.Sc. Eng. Hons (Peradeniya), M.Sc. (Moratuwa), Ph.D. (Moratuwa

X close

C. R. de Silva,

University of Moratuwa, LK
About C. R.

Senior Lecturer in Computer Science and Engineering

 

C. Eng., MIE(SL), B.Sc. Eng. Hons (Moratuwa), M.Eng. (NTU), Ph.D. (NTU)

X close

C. D. Gamage

University of Moratuwa, LK
About C. D.

Senior Lecturer in Computer Science and Engineering

 

C. Eng., MIE(SL), B.Sc. Eng. Hons (Moratuwa), M.Eng. (AIT), Ph.D. (Monash)

X close

Abstract

In this experimental research, the effects of gray-level quantization and tiling window size on 22 gray-level co-occurrence matrix features were investigated in the context of automated woven fabric defect detection. A dataset comprising 1426 128×128 images was used, in which defective and the defect-free images were split in a 50:50 ratio. Experiments were carried out with seven quantization levels (

How to Cite: Pallemulla, P.S.H., Sooriyaarachchi, S.J., de Silva, C.R. and Gamage, C.D., 2021. Defect Detection in Woven Fabrics by Analysis of Co-occurrence Texture Features as a Function of Gray-level Quantization and Window Size. Engineer: Journal of the Institution of Engineers, Sri Lanka, 54(4), pp.55–64. DOI: http://doi.org/10.4038/engineer.v54i4.7470
Published on 30 Dec 2021.
Peer Reviewed

Downloads

  • PDF (EN)

    comments powered by Disqus