Fabric Defect Identification Based on 2D Empirical Mode Decomposition

DOI

10.2991/epee-16.2016.61How to use a DOI?

Keywords

2D empirical mode decomposition; intrinsic mode component; fabric defect

Abstract

Fabric defect identification has constituted a key part in the online quality control regarding the textile manufacturing process. Focusing on the limitations of conventional fabric defect identification methods in representing local geometry of fabric defects, a fully adaptive image processing technique called two-dimensional empirical mode decomposition is introduced in this paper to extract the identification feature of fabric defect and segment the fabric defect region. The firstly decomposed intrinsic mode component is capable of maintaining fine-scale patterns of the fabric defect, while the secondly decomposed intrinsic mode component possesses the main energy of medium-scale patterns. As a result, both energy and local scale parameters along warp or weft direction are derived from either first intrinsic mode component or second intrinsic mode component to locate the defect pixels in the fabric. Simulation results have shown that the proposed method is characterized by high accuracy with fast computational speed.

Copyright

© 2016, 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  - Shuaijun Wang
AU  - Ye Yuan
AU  - Hongli Dun
PY  - 2016/10
DA  - 2016/10
TI  - Fabric Defect Identification Based on 2D Empirical Mode Decomposition
BT  - Proceedings of the 2016 International Conference on Energy, Power and Electrical Engineering
PB  - Atlantis Press
SP  - 274
EP  - 277
SN  - 2352-5401
UR  - https://doi.org/10.2991/epee-16.2016.61
DO  - 10.2991/epee-16.2016.61
ID  - Wang2016/10
ER  -