[1]杨达,狄岚,赵树志,等.基于结构相似性与模板校正的织物瑕疵检测方法[J].智能系统学报,2020,15(3):475-483.[doi:10.11992/tis.201810011]
 YANG Da,DI Lan,ZHAO Shuzhi,et al.Fabric defect detection based on structural similarity and template correction[J].CAAI Transactions on Intelligent Systems,2020,15(3):475-483.[doi:10.11992/tis.201810011]
点击复制

基于结构相似性与模板校正的织物瑕疵检测方法(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第15卷
期数:
2020年3期
页码:
475-483
栏目:
学术论文—智能系统
出版日期:
2020-05-05

文章信息/Info

Title:
Fabric defect detection based on structural similarity and template correction
作者:
杨达1 狄岚1 赵树志1 梁久祯2
1. 江南大学 数字媒体学院,江苏 无锡 214122;
2. 常州大学 信息科学与工程学院,江苏 常州 213164
Author(s):
YANG Da1 DI Lan1 ZHAO Shuzhi1 LIANG Jiuzhen2
1. School of Digital Media, Jiangnan University, Wuxi 214122, China;
2. School of Information Science and Engineering, Changzhou University, Changzhou 213164, China
关键词:
结构相似性周期性模板校正单位模板自动分割相似关系阈值分割瑕疵检测
Keywords:
structural similarityperiodictemplate correctionunit templateautomatic segmentationsimilarity relationshipthreshold segementationdefect inspection
分类号:
TS131.9;TP18
DOI:
10.11992/tis.201810011
摘要:
针对复杂的具有周期性结构的织物瑕疵检测,提出一种基于结构相似性与模板校正的织物瑕疵检测方法。通过图案的周期性,得到图案单位模板大小,再对图像自动分割,同时应用基于模板校正的方法以减少晶格之间未对准的影响,并构建均值模板。通过计算所有晶格间的结构相似性,并将相似关系通过传递闭包的方式得到等价关系,再进行晶格间的聚类。之后通过阈值分割方法,完成瑕疵区域的检测。通过实验表明,改进后的算法检测效果较好,本文算法显著提高了样本的查准率。
Abstract:
Focusing on the detection of defects in textiles with complex periodic patterns, a fabric defect detection method based on structural similarity and template correction is proposed. The unit template size of the pattern is obtained according to the periodicity of the pattern texture. Then, the image is divided adaptively. At the same time, template correction is applied to reduce the effect of misalignment between grids. In addition, an average template is established. The structural similarity between all the lattices is calculated, and such similarity is observed in the pattern of the closure packet and used to obtain the equivalence relation. Then, the clustering between all the lattices is performed. Furthermore, the detection of the defect region is completed using the proposed threshold segmentation method. Experiments show that the proposed algorithm has better detection effect than other algorithms and significantly improves the precision ratio of the sample.

参考文献/References:

[1] TSAI D M, CHEN Mingchun, LI Weichen, et al. A fast regularity measure for surface defect detection[J]. Machine vision and applications, 2012, 23(5): 869-886.
[2] 步红刚, 黄秀宝, 汪军. 基于多分形特征参数的织物瑕疵检测[J]. 计算机工程与应用, 2007, 43(36): 233-237
BU Honggang, HUANG Xiubao, WANG Jun. Fabric defects detection based on multiple fractal features[J]. Computer engineering and applications, 2007, 43(36): 233-237
[3] MAK K L, PENG P, YIU K F C. Fabric defect detection using morphological filters[J]. Image and vision computing, 2009, 27(10): 1585-1592.
[4] AZIZ M A, HAGGAG A S, SAYED M S. Fabric defect detection algorithm using morphological processing and DCT[C]//Proceedings of the 2013 1st International Conference on Communications, Signal Processing, and their Applications. Sharjah, United Arab Emirates, 2013: 1-4.
[5] CHAN C H, PANG G K H. Fabric defect detection by Fourier analysis[J]. IEEE transactions on industry applications, 2000, 36(5): 1267-1276.
[6] KUMAR A, PANG G. Defect detection in textured materials using Gabor filters[C]//Proceedings of the Conference Record of the 2000 IEEE Industry Applications Conference. Thirty-Fifth IAS Annual Meeting and World Conference on Industrial Applications of Electrical Energy. Rome, Italy, 2002.
[7] ZUO Haiqin, WANG Yujie, YANG Xuezhi, et al. Fabric defect detection based on texture enhancement[C]//Proceedings of the 2012 5th International Congress on Image and Signal Processing. Chongqing, China, 2012: 876-880.
[8] COHEN F S, FAN Z, ATTALI S. Automated inspection of textile fabrics using textural models[J]. IEEE transactions on pattern analysis and machine intelligence, 1991, 13(8): 803-808.
[9] ZHOU Jian, SEMENOVICH D, SOWMYA A, et al. Sparse dictionary reconstruction for textile defect detection[C]//Proceedings of the 2012 11th International Conference on Machine Learning and Applications. Boca Raton, USA, 2012: 21-26.
[10] KANG Zhiqiang, YUAN Chaohui, YANG Qian. The fabric defect detection technology based on wavelet transform and neural network convergence[C]//Proceedings of 2013 IEEE International Conference on Information and Automation. Yinchuan, China, 2013: 597-601.
[11] GHOSH A, GUHA T, BHAR R B, et al. Pattern classification of fabric defects using support vector machines[J]. International journal of clothing science and technology, 2011, 23(2/3): 142-151.
[12] CHETVERIKOV D. Pattern regularity as a visual key[J]. Image and vision computing, 2000, 18(12): 975-985.
[13] NGAN H Y T, PANG G K H, YUNG S P, et al. Wavelet based methods on patterned fabric defect detection[J]. Pattern recognition, 2005, 38(4): 559-576.
[14] NGAN H Y T, PANG G K H. Novel method for patterned fabric inspection using Bollinger bands[J]. Optical engineering, 2006, 45(8): 087202.
[15] NGAN H Y T, PANG G K H. Regularity analysis for patterned texture inspection[J]. IEEE transactions on automation science and engineering, 2009, 6(1): 131-144.
[16] NG M K, NGAN H Y T, YUAN Xiaoming, et al. Patterned fabric inspection and visualization by the method of image decomposition[J]. IEEE transactions on automation science and engineering, 2014, 11(3): 943-947.
[17] CHANG Xingzhi, GU Chengxi, LIANG Jiuzhen, et al. Fabric defect detection based on pattern template correction[J]. Mathematical problems in engineering, 2018, 2018: 3709821.
[18] TSANG C S C, NGAN H Y T, PANG G K H. Fabric inspection based on the Elo rating method[J]. Pattern recognition, 2016, 51: 378-394.
[19] 马慧, 王科俊. 采用旋转校正的指静脉图像感兴趣区域提取方法[J]. 智能系统学报, 2012, 7(3): 230-234
MA Hui, WANG Kejun. A region of interest extraction method using rotation rectified finger vein images[J]. CAAI transactions on intelligent systems, 2012, 7(3): 230-234
[20] WANG Zhou, BOVIK A C, SHEIKH H R, et al. Image quality assessment: from error visibility to structural similarity[J]. IEEE transactions on image processing, 2004, 13(4): 600-612.
[21] HUANG Y J, POWERS R, MONTELIONE G T. Protein NMR recall, precision, and F-measure scores (RPF scores): structure quality assessment measures based on information retrieval statistics[J]. Journal of the American chemical society, 2005, 127(6): 1665-1674.

备注/Memo

备注/Memo:
收稿日期:2018-10-12。
基金项目:江苏省研究生科研与实践创新计划项目(SJCX19_0794)
作者简介:杨达,硕士研究生,主要研究方向为图像处理;狄岚,副教授,主要研究方向为模式识别和数字图像处理。参与国家级及省部级科研项目6项。江苏省“六大人才高峰”资助对象,获得省级自然科学学术奖1次,中国行业联合会科学技术奖3次。发表学术论文40余篇;赵树志,硕士研究生,主要研究方向为机器视觉
通讯作者:狄岚.E-mail:dilan@jiangnan.edu.cn
更新日期/Last Update: 1900-01-01