Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/77599
Title: Computer vision techniques for detecting fabric defects
Authors: Wong, WK 
Jiang, JL
Keywords: Compact dictionary
Fabric defect detection
Nonlocal self-similarity
Principle component analysis
Sparse coding
Issue Date: 2017
Publisher: Woodhead Publishing, an imprint of Elsevier
Source: In WK Wong (Ed.), Applications of computer vision in fashion and textiles, p. 3-15. Duxford, U.K. : Woodhead Publishing, an imprint of Elsevier, 2017 How to cite?
Abstract: Fabric defect detection is vital to fabric quality control. In recent two decades, although various detection techniques have been proposed, these techniques are limited to fabrics with solid colors in controlled environment. In other words, most of them cannot be applied to fabrics with different patterns under controlled environment. This chapter presents a novel fabric defect detection technique, called nonlocal self-similarity-based spare coding (NSSSC), which can effectively detect defects on fabrics with solid color with uneven illumination distribution, which always happen in real-life manufacturing environment, and stripe pattern. The experimental results demonstrated that the NSSSC outperforms several state-of-the-art fabric defect detection methods.
URI: http://hdl.handle.net/10397/77599
ISBN: 9780081012185
9780081012178
DOI: 10.1016/B978-0-08-101217-8.00003-8
Appears in Collections:Book Chapter

Access
View full-text via PolyU eLinks SFX Query
Show full item record

Page view(s)

19
Citations as of Sep 18, 2018

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.