Journal of Textile Research ›› 2019, Vol. 40 ›› Issue (02): 38-44.doi: 10.13475/j.fzxb.20180607007

• Textile Engineering • Previous Articles     Next Articles

Fabric defect detection based on improved local adaptive contrast method

DU Shuai1, LI Yueyang1(), WANG Mengtao1, LUO Haichi2, JIANG Gaoming1   

  1. 1. Engineering Research Center for Knitting Technology, Ministry of Education, Jiangnan univevsity, Wuxi Jiangsu 214122, China
    2. Key Laboratory of Advanced Process Control for Light Industry, Ministry of Education, Jiangnan University, Wuxi, Jiangsu 214122, China
  • Received:2018-06-25 Revised:2018-08-02 Online:2019-02-15 Published:2019-02-01
  • Contact: LI Yueyang E-mail:lyueyang@jiangnan.edu.cn

RichHTML

8

PDF (PC)

202

Abstract:

In order to improve the fabric defect detection accuracy and detection effect, a background estimation method based on the most similar neighborhood patch was used to improve the detection rate. Firstly, the image was preprocessed by homomorphic filtering. Then, each pixel of the filtered image was taken as center point and window size of 11 pixel×39 pixel was taken as the central region. By calculation the similarity between the central region and the surrounding neighborhood to find out the neighborhood which was most similar to central region. So then, the purpose of background estimation was achieved. The background-difference principle was used to obtain the target image and the method of threshold segmentation and morphological was used in the image. Finally, the defection results were obtained. The experiment results show that the method is superior to the traditional detection method, not only can detection the defect image in complex background, but also has good detection results for fabric defect images under influence of external factors and different fabric weaves, the detection rate can reach 98%, and with high recognition rate, applicability and a certain degree of anti-interference.

Key words: fabric defect, defect detection, adaptive local contrast method, background difference method, threshold segmentation

CLC Number: 

  • TP391.4

Fig.1

Fabric defect image"

Fig.2

Comparison between original image and homomorphic filtering image. (a)Original image;(b)Homomorphic filtering image"

Fig.3

Principle of detection algorithm"

Fig.4

Fabric defect detection results in complex background. (a) Clip mark;(b) Detection results in clip mark;(c) Fluff;(d) Detection results in fluff; (e) Filling b;(f) Detection results in Filling b"

Fig.5

Compared detection results for several defect detection methods. (a)External fiber; (b) Result of (a) by using method of document[1]; (c) Result of (a) by using method of document[5]; (d)Result of (a);(e)Coarse pick; (f) Result of (e) by using method of document[1]; (g) Result of (e) by using method of document[5]; (h)Result of (e);(i)Filling floats;(j) Result of (i) by using method of document[1]; (k) Result of (i) by using method of document[5]; (l)Result of (i)"

Fig.6

z1 weave defect detection results. (a) Yarn was broken in left;(b) Detection results of (a);(c) Yarn was broken in middle;(d) Detection results of (c);(e) Yarn was broken in right;(f) Detection results of (e)"

Fig.7

z2 weave defect detection results. (a) Yarn was broken in left;(b) Detection results of (a);(c) Yarn was broken in middle;(d) Detection results of (c);(e) Yarn was broken in right; (f) Detection results of (e)"

Fig.8

z3 weave defect detection results. (a) The yarn was broken in left;(b) Detection results of (a);(c) The yarn was broken in middle;(d) Detection results of (c);(e) The yarn was broken in right;(f) Detection results of (e)"

Tab.1

Statistics for defect detection results"

图像类型 检测结果/张 检测率/% 综合检
测率/%
未检测出 检测出 准确率 虚警率
含疵点 2 56 96.55 - 98
不含疵点 0 42 100 0
[1] KUMAR A, PANG G K H. Defect detection in textured materials using Gabor filters[J]. IEEE Transactions on Systems Man and Cybernetics: Part B: Cybernetics, 2002,32(5):553-570.
doi: 10.1109/TSMCB.2002.1033176
[2] CAO Y, LIU R M, YANG J. Small target detection using two-dimensional least mean square (TDLMS) filter based on neighborhood analysis[J]. International Journal of Infrared & Millimeter Waves, 2008,29(2):188-200.
[3] 尉苗苗, 李岳阳, 蒋高明, 等. 应用最优Gabor滤波器的经编织物疵点检测[J]. 纺织学报, 2016,37(11):48-54.
YU Miaomiao, LI Yueyang, JIANG Gaoming, et al. Warp knit fabric defect detection method based on optimal Gabor filter[J]. Journal of Textile Research, 2016,37(11):48-54.
[4] 李岳阳, 蒋高明, 丛洪莲, 等. 基于最优Gabor滤波器的经编织物瑕疵检测方法:105205828 A[P]. 2015 -10-20.
LI Yueyang, JIANG Gaoming, CONG Honglian, et al. Warp knit fabric defect detection method based on optimal Gabor filter: 105205828 A[P]. 2015 -10-20.
[5] TONG L, WONG W K, WONG C K. Differential evolution-based optimal Gabor filter model for fabric inspection[J]. Neurocomputing, 2016,173:1386-1401.
doi: 10.1016/j.neucom.2015.09.011
[6] CHEN C L P, LI H, WEI Y, et al. A local contrast method for small infrared target detection[J]. IEEE Transactions on Geoscience & Remote Sensing, 2014,52(1):574-581.
[7] 许海洋, 马龙龙, 吴健. 基于背景估计和边缘检测的文档图像二值化[J]. 计算机应用与软件, 2014,31(8):196-200.
XU Haiyang, MA Longlong, WU Jian. Document image binarisation based on back ground estimation and edge detection[J]. Computer Applications and Software, 2014,31(8):196-200.
[8] MENG B, ZHANG H, MAO Z, et al. FPGA implementation of local contrast method for infrared small target detection [C]// IEEE International Conference on Electronic Measurement & Instruments.New York:IEEE, 2016: 1293-1297.
[9] WANG Y, XU X, YUE N, et al. Edge-preserving background estimation using most similar neighbor patch for small target detection[C]// Chinese Conference on Computer Vision. Bolin:Springer Publishing Company, 2017: 85-89
[10] GONZALEZ R C, WOODS R E, EDDINS S L. Digital Image Processing Using MatLab[M]. 4th ed. Beijing:Publishing House of Electronics Industry, 2003: 94,347-359, 404-412.
[11] 徐黎明, 吕继东. 基于同态滤波和K均值聚类算法的杨梅图像分割[J]. 农业工程学报, 2015,31(14):202-208.
XU Liming, LV Jidong. Bayberry image segmentation based on homomorphic filtering and K-means clustering algorithm[J]. Transactions of the Chinese Society of Agricultural Engineering, 2015,31(14):202-208.
[12] 杜磊, 李立轻, 汪军, 等. 几种基于图像自适应阈值分割的织物疵点检测方法比较[J]. 纺织学报, 2014,35(6):56-61.
DU Lei, LI Liqing, WANG Jun, et al. Comparison of several fabric defect detection methods based on image self-adaptive threshold segmentation[J]. Journal of Textile Research, 2014,35(6):56-61.
[13] 刘建立, 左保齐. 基于小波变换和阈值分割的织物疵点边缘检测[J]. 丝绸, 2006(8):42-44.
LIU Jianli, ZUO Baoqi. Edge detection of fabric defects based on wavelet transform and threshold segmentation algorithm[J]. Journal of Silk, 2006(8):42-44.
[1] ZHU Lei, REN Mengfan, PAN Yang, LI Botao. Fabric defect detection based on similarity location and superpixel segmentation [J]. Journal of Textile Research, 2020, 41(10): 58-66.
[2] DI Lan, YANG Da, LIANG Jiuzhen, MA Mingyin. Fabric defect detection method based on primitive segmentation and Gabor filtering [J]. Journal of Textile Research, 2020, 41(09): 59-66.
[3] ZHOU Wenming, ZHOU Jian, PAN Ruru. Yarn-dyed fabric defect detection based on context visual saliency [J]. Journal of Textile Research, 2020, 41(08): 39-44.
[4] YANG Enjun, LIAO Yihui, LIU Andong, YU Li. Detection for fabric defects based on low-rank decomposition [J]. Journal of Textile Research, 2020, 41(05): 72-78.
[5] LU Hao, CHEN Yuan. Surface defect detection method of carbon fiber prepreg based on machine vision [J]. Journal of Textile Research, 2020, 41(04): 51-57.
[6] WANG Wensheng, LI Tianjian, RAN Yuchen, LU Ying, HUANG Min. Method for position detection of cheese yarn rod [J]. Journal of Textile Research, 2020, 41(03): 160-167.
[7] JING Junfeng, ZHANG Junyang, ZHANG Huanhuan, SU Zebin. Defect detection on surface of draw texturing yarn packages in gradient space [J]. Journal of Textile Research, 2020, 41(02): 44-51.
[8] ZHANG Huanhuan, MA Jinxiu, JING Junfeng, LI Pengfei. Fabric defect detection method based on improved fast weighted median filtering and K-means [J]. Journal of Textile Research, 2019, 40(12): 50-56.
[9] XIAO Zhitao, GUO Yongmin, GENG Lei, WU Jun, ZHANG Fang, WANG Wen, LIU Yanbei. Internal defect detection method for thin test pieces of woven laminated composites based on ultrasonic phased array [J]. Journal of Textile Research, 2019, 40(11): 81-87.
[10] ZHU Hao, DING Hui, SHANG Yuanyuan, SHAO Zhuhong. Defect detection algorithm for multiple texture hierarchical fusion fabric [J]. Journal of Textile Research, 2019, 40(06): 117-124.
[11] WANG Wendi, XIN Binjie, DENG Na, LI Jiaping, LIU Ningjuan. Identification and application of yarn hairiness using adaptive threshold method under single vision [J]. Journal of Textile Research, 2019, 40(05): 150-156.
[12] XU Yang, ZHU Zhichao, SHENG Xiaowei, YU Zhiqi, SUN Yize. Improvement recognition method of vamp's feature points based on machine vision [J]. Journal of Textile Research, 2019, 40(03): 168-174.
[13] HU Keman, LUO Siolong, HU Haiyan. Improved algorithm for fabric defect detection based on Canny operator [J]. Journal of Textile Research, 2019, 40(01): 153-158.
[14] . Fabric defect inspection based on modified discriminant complete local binary pattern and lattice segmentation [J]. Journal of Textile Research, 2018, 39(09): 57-64.
[15] . Segmentation of fabric defect images based on improved frequency-tuned salient algorithm [J]. JOURNAL OF TEXTILE RESEARCH, 2018, 39(05): 125-131.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
京ICP备14006648号
Copyright 2021 © Editorial office of Journal of Textile Research
Supported by Beijing Magtech Co.Ltd