Detection of varied defects in diverse fabric images via modified RPCA with noise term and defect prior
International Journal of Clothing Science and Technology
ISSN: 0955-6222
Article publication date: 1 August 2016
Abstract
Purpose
The purpose of this paper is to present a novel method for fabric defect detection.
Design/methodology/approach
The method based on joint low-rank and spare matrix recovery, since patterned fabric is manufactured by a set of predefined symmetry rules, and it can be seen as the superposition of sparse defective regions and low-rank defect-free regions. A robust principal component analysis model with a noise term is designed to handle fabric images with diverse patterns robustly. The authors also estimate a defect prior and use it to guide the matrix recovery process for accurate extraction of various fabric defects.
Findings
Experiments on plain and twill, dot-, box- and star-patterned fabric images with various defects demonstrate that the method is more efficient and robust than previous methods.
Originality/value
The authors present a RPCA-based model for fabric defects detection, and show how to incorporate defect prior to improve the detection results. The authors also show that more robust detection and less running time can be obtained by introducing a noise term into the model.
Keywords
Acknowledgements
The authors would like to thank Huanhuan Zhang for her images of TILDA Textile Texture Database as well as Henry Y.T. Ngan for his diverse fabric images. Junjie Cao is supported by the NSFC China (61363048). Zhijie Wen is supported by the NSFC China (11471208). Bo Li is supported by the NSFC China (61262050) and NSFC China (61562062). Xiuping Liu is supported by the NSFC China (61370143).
Citation
Cao, J., Wang, N., Zhang, J., Wen, Z., Li, B. and Liu, X. (2016), "Detection of varied defects in diverse fabric images via modified RPCA with noise term and defect prior", International Journal of Clothing Science and Technology, Vol. 28 No. 4, pp. 516-529. https://doi.org/10.1108/IJCST-10-2015-0117
Publisher
:Emerald Group Publishing Limited
Copyright © 2016, Emerald Group Publishing Limited