纺织学报 ›› 2020, Vol. 41 ›› Issue (09): 59-66.doi: 10.13475/j.fzxb.20191204308

• 纺织工程 • 上一篇    下一篇

基于图元分割与Gabor滤波的织物瑕疵检测方法

狄岚1,2(), 杨达1, 梁久祯3, 马明寅1   

  1. 1.江南大学 人工智能与计算机学院, 江苏 无锡 214122
    2.道路交通安全公安部重点实验室, 江苏 无锡 214151
    3.常州大学 信息科学与工程学院, 江苏 常州 213164
  • 收稿日期:2019-12-17 修回日期:2020-06-04 出版日期:2020-09-15 发布日期:2020-09-25
  • 作者简介:狄岚(1965—),女,副教授。主要研究方向为模式识别与图像处理。E-mail: dilan@jiangnan.edu.cn。
  • 基金资助:
    江苏省研究生科研与实践创新计划项目(SJCX19_0794);道路交通安全公安部重点实验室开放课题基金资助项目(2020ZDSYSKFKT03-2)

Fabric defect detection method based on primitive segmentation and Gabor filtering

DI Lan1,2(), YANG Da1, LIANG Jiuzhen3, MA Mingyin1   

  1. 1. School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, Jiangsu 214122, China
    2. Key Laboratory of Ministry of Public Security for Road Traffic Safety, Wuxi, Jiangsu 214151, China
    3. College of Information Science and Engineering, Changzhou University, Changzhou, Jiangsu 213164, China
  • Received:2019-12-17 Revised:2020-06-04 Online:2020-09-15 Published:2020-09-25

RichHTML

7

PDF (PC)

91

摘要：

为实现含复杂图案织物的自动化检测,提出基于图元分割与Gabor滤波的织物瑕疵检测方法,对具有复杂周期变化图案的织物进行检测。根据图像纹理的周期变化规律,确定图案单位模板大小,即包含一个周期图案的晶格。对图像进行自适应分割,并通过图元分割获得单元图像元素。通过Gabor滤波器生成特征的响应分布,获取理想的模板晶格,根据提出的投票程序,通过分析其特征向量的Manhattan根据距离图元晶格差异的分布来识别瑕疵图元晶格。实验结果表明:检测方法对星形和箱形图案的织物样本数据集上检测效果较好,显著提高了样本的查全率。

关键词: 图元分割, Gabor滤波, 织物瑕疵, 瑕疵检测

Abstract:

In order to deal with the complex fabric defect detection with periodic variation pattern, a fabric defect detection method based on primitive segmentation and Gabor filtering was proposed. The template size of the pattern unit was determined according to the periodic variation of the image texture, i.e. a lattice containing a periodic pattern. The image was adaptively segmented, and the image elements of the smaller unit are obtained by the primitive segmentation. The response distribution given by the Gabor filter to the convolutional lattice produced an ideal template lattice. According to the proposed voting procedure, the lattice of the defect is identified by analyzing the distribution of the lattice differences represented by the Manhattan distance of the eigenvectors. Experiments show that the method has better detection effect on the fabric samples of star and box patterns, and significantly reducing the recall rate of the samples.

Key words: primitive segmentation, Gabor filtering, fabric defect, defect inspection

中图分类号: 

  • TS131.9

图1

获得图像单位模板大小"

图2

星状图的图元分割"

图3

Gabor 滤波器卷积投影"

图4

全部晶格卷积后的特征向量"

表1

不同算法对星状图织物瑕疵检测结果"

星状图 MTPR/
%		 MFPR/
%		 MPPV/
%		 MNPV/
%		 f值/
%		 方法
86 2 20 99 33 本文算法
31 16 1 99 5 BB
断端 32 2 11 100 5 RB
73 4 9 100 5 WGIS
1 0 0 99 15 ER
81 1 26 99 40 本文算法
33 15 1 100 4 BB
破洞 43 3 8 100 5 RB
26 7 3 100 2 WGIS
4 0 0 99 0 ER
82 0 15 99 2 本文算法
6 0 22 98 10 BB
细条纹 3 0 27 98 6 RB
0 3 0 99 0 WGIS
45 2 12 99 2 ER
75 1 71 99 73 本文算法
10 16 2 96 56 BB
粗条纹 21 3 13 97 54 RB
89 19 20 100 8 WGIS
38 1 57 99 29 ER

图5

5种方法对星状图检测的MFPR-MTPR图"

图6

不同算法的检测结果"

表2

不同算法对盒状图织物瑕疵检测结果"

盒状图 MTPR/
%		 MFPR/
%		 MPPV/
%		 MNPV/
%		 f值/
%		 方法
79 2 38 99 51 本文算法
4 2 4 98 3 BB
断端 49 1 56 99 6 RB
64 8 14 99 0 WGIS
1 0 0 98 8 ER
68 1 30 99 57 本文算法
8 2 3 99 4 BB
破洞 10 0 47 99 11 RB
2 1 4 99 0 WGIS
0 0 0 99 16 ER
73 4 15 99 24 本文算法
31 0 29 99 31 BB
细条纹 32 0 30 99 31 RB
26 24 1 99 2 WGIS
5 4 2 97 3 ER
81 3 33 97 47 本文算法
8 2 8 97 41 BB
粗条纹 58 1 68 99 31 RB
99 14 15 100 5 WGIS
2 0 0 98 61 ER

图7

5种方法对盒状图检测的MFPR-MTPR图"

[1] BU H G, WANG J, HUANG X B. Fabric defect detection based on multiple fractal features and support vector data description[J]. Engineering Applications of Artificial Intelligence, 2009,22(2):224-235.
doi: 10.1016/j.engappai.2008.05.006
[2] 田承泰, 步红刚, 汪军, 等. 基于时间序列分形特征的织物瑕疵检测[J]. 纺织学报, 2010(5):49-52,59.
TIAN Chengtai, BU Honggang, WANG Jun, et al. Fabric defect detection based on frature of timie series[J]. Journal of Textile Research, 2010(5):49-52,59.
[3] 张波, 汤春明. 基于相对总变差模型与自适应形态学的织物瑕疵检测[J]. 纺织学报, 2017,38(5):145-149.
ZHANG Bo, TANG Chunming. Fabric defect detection based on relative total variation model and adaptive mathematical morphology[J]. Journal of Textile Research, 2017,38(5):145-149.
[4] ZHANG C S, KE W, WANG G H. Automatic recognition analysis of fabric structure based on GLCM and BP neural network[J]. Advanced Materials Research, 2011, 332-334:1167-1170.
[5] ZHU D, PAN R, GAO W, et al. Yarn-dyed fabric defect detection based on autocorrelation function and GLCM[J]. Autex Research Journal, 2015,15(3):226-232.
[6] MAK K L, PENG P, YIU K F C. Fabric defect detection using morphological filters[J]. Image & Vision Computing, 2009,27(10):1585-1592.
[7] CHETVERIKOV D, HANBURY A. Finding defects in texture using regularity and local orientation[J]. Pattern Recognition, 2002,35(10):2165-2180.
[8] YANG X Z, PANG G K H, YUNG N H C. Discriminative fabric defect detection using adaptive wavelets[J]. Optical Engineering, 2002,41(12):3116-3126.
[9] ZUO H, WANG Y, YANG X, et al. Fabric defect detection based on texture enhancement[C]// 2012 5th International Congress on Image and Signal Processing (CISP). Philadelphia: IEEE, 2012: 876-880.
[10] NAVARRO P J, FERNÁNDEZISLA C, ALCOVER P M, et al. Defect detection in textures through the use of entropy as a means for automatically selecting the wavelet decomposition level[J]. Sensors, 2016,16(8):21.
[11] ZHU Dandan, PAN Ruru, GAO Weidong. Fabric defect detection using characteristic spectrum of Fourier transform and correlation coefficient[J]. Computer Engineering and Applications, 2014,50(10):866-73.
[12] 屈博, 卢朝阳, 李静, 等. 一种改进的多通道Gabor滤波器布匹瑕疵检测方法[J]. 纺织学报, 2009,30(12):37-40.
QU Bo, LU Zhaoyang, LI Jing, et al. An improved multichannel Gabor filter algorithm for fabric defect detection[J]. Journal of Textile Research, 2009,30(12):37-40.
[13] MAK K L, PENG P, YIU K F C. Fabric defect detection using multi-level tuned-matched Gabor filters[J]. Journal of Industrial and Management Optimization, 2012,8(2):325-341.
doi: 10.3934/jimo.2012.8.325
[14] MAK K L, PENG P. An automated inspection system for textile fabrics based on Gabor filters[J]. Robotics and Computer Integrated Manufacturing, 2008,24(3):359-369.
[15] BU H G, HUANG X B, WANG J, et al. Detection of fabric defects by auto-regressive spectral analysis and support vector data description[J]. Textile Research Journal, 2010,80(7):579-589.
[16] SERAFIM A F L. Multiresolution pyramids for segmentation of natural images based on autoregressive models: application to calf leather classification[C]// Proceedings of Conference of the IEEE Industrial Electronics Society. Philadelphia: IEEE, 2002: 1842-1847.
[17] HAJIMOWLANA S H, MUSCEDERE R, JULLIEN G A, et al. 1D autoregressive modeling for defect detection in web inspection systems[C]// Midwest Symposium on Systems & Circuits. Washington: IEEE Computer Society, 1998: 318-321.
[18] DENG H, CLAUSI D A. Gaussian MRF rotation-invariant features for image classification[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004,26(7):951-955.
pmid: 18579954
[19] COHEN F S, FAN Z, ATTALI S, et al. Automated inspection of textile fabrics using textural models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991,13(8):803-808.
[20] 纪旋, 梁久祯, 侯振杰, 等. 基于模板校正与低秩分解的纺织品瑕疵检测方法[J]. 模式识别与人工智能, 2019,32(3):78-87.
JI Xuan, LIANG Jiuzhen, HOU Zhenjie, et al. Fabric defect detection based on template correction and low-rank decomposiont[J]. Pattern Recognition and Artificial Intelligence, 2019,32(3):78-87.
[21] 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.
doi: 10.1016/j.patcog.2004.07.009
[22] NGAN H Y T, PANG G K H. Novel method for patterned fabric inspection using Bollinger bands[J]. Optical Engineering, 2006,45(8):087202.
[23] NGAN H, PANG G. Regularity analysis for patterned texture inspection[J]. IEEE Transactions on Automation Science and Engineering, 2009,6(1):131-144.
[24] NG M K, NGAN H Y T, YUAN X, et al. Patterned fabric inspection and visualization by the method of image decomposition[J]. IEEE Transactions on Automation Science & Engineering, 2014,11(3):943-947.
[25] 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.
[26] 刘威, 常兴治, 梁久祯, 等. 基于局部最优分析的纺织品瑕疵检测方法[J]. 模式识别与人工智能, 2018(2):182-189.
LIU Wei, CHANG Xingzhi, LIANG Jiuzhen, et al. Textile defect detection method based on local optimal analysis[J]. Pattern Recognition and Artificial Intelligence, 2018 (2):182-189.
[1] 赵树志 狄岚 何锐波. 基于改进判别性完整局部二值模式与格分割的织物瑕疵检测方法[J]. 纺织学报, 2018, 39(09): 57-64.
[2] 吴莹 汪军. 基于K-SVD学习字典的机织物纹理表征及应用[J]. 纺织学报, 2018, 39(02): 165-170.
[3] 张波 汤春明. 基于相对总变差模型与自适应形态学的织物瑕疵检测[J]. 纺织学报, 2017, 38(05): 145-149.
[4] 王传桐 胡峰 徐启永 吴雨川 余联庆. 采用Gabor滤波簇和等距映射算法的织物疵点检测方法[J]. 纺织学报, 2017, 38(03): 162-167.
[5] 毛兆华 汪军 周建 卜佳仙 陈霞 李立轻. 应用非负字典学习的机织物瑕疵检测算法[J]. 纺织学报, 2016, 37(3): 144-149.
[6] 周建 王静安 高卫东. 应用局部纹理特征的无监督织物瑕疵检测算法[J]. 纺织学报, 2016, 37(12): 43-48.
[7] 董蓉 李勃 徐晨. 应用积分图的织物瑕疵检测快速算法[J]. 纺织学报, 2016, 37(11): 141-147.
[8] 王钢 周建 汪军 卜佳仙 李立轻 陈霞. 基于奇异值分解的机织物瑕疵检测算法[J]. 纺织学报, 2014, 35(7): 61-0.
[9] 田承泰;步红刚;汪 军;陈 霞;. 基于时间序列分形特征的织物瑕疵检测[J]. 纺织学报, 2010, 31(5): 44-47.
[10] 杨晓波. 基于Gabor滤波器的织物疵点检测[J]. 纺织学报, 2010, 31(4): 55-59.
[11] 屈博;卢朝阳;李静;崔玲玲;周峰江. 一种改进的多通道Gabor滤波器布匹瑕疵检测方法[J]. 纺织学报, 2009, 30(12): 37-40.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
京ICP备14006648号　 京公网安备11010502044800号
版权所有 © 2021 《纺织学报》编辑部
地址： 北京市朝阳区延静里中街3号主楼6层《纺织学报》杂志社　邮政编码：100025　
电话：010-65017711,65917740　传真：010-65016539　Email:fangzhixuebao@vip.126.com
本系统由北京玛格泰克科技发展有限公司设计开发