点击次数：
论文类型：期刊论文
发表时间：2016-08-01
发表刊物：INTERNATIONAL JOURNAL OF CLOTHING SCIENCE AND TECHNOLOGY
收录刊物：SCIE、EI、Scopus
卷号：28
期号：4
页面范围：516-529
ISSN号：0955-6222
关键字：Defect detection; Defect prior; Fabric with complex patterns; Robust principal component analysis
摘要：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.