Fabric defect detection based on wavelet transform and k-means

DOI

10.2991/icecee-15.2015.130How to use a DOI?

Keywords

Wavelet Transform; k-means; Fabric Defect

Abstract

A novel method based on wavelet transform and k-means is proposed to solve the problem of automated fabric defect detection which is more essential and important in assuring the fabric quality. Firstly, the fabric images are processed using wavelet decomposition algorithm, and the produced wavelet coefficients are used to restructure the new images using wavelet thresholding denoising. Secondly, the obtained new images are segmented by applying the k-means algorithm. The results demonstrate that the proposed scheme is able to efficiently locate the position of fabric defect and segment the defect.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Huanuan Zhang
AU  - Juan Zhao
AU  - Renzhong Li
AU  - Junfeng Jing
AU  - Pengfei Li
PY  - 2015/06
DA  - 2015/06
TI  - Fabric defect detection based on wavelet transform and k-means
BT  - Proceedings of the 2015 International Conference on Electrical, Computer Engineering and Electronics
PB  - Atlantis Press
SP  - 649
EP  - 653
SN  - 2352-538X
UR  - https://doi.org/10.2991/icecee-15.2015.130
DO  - 10.2991/icecee-15.2015.130
ID  - Zhang2015/06
ER  -