We introduce a real-time machine vision system we developed with the aim of detecting defects in functional textile fabrics with good precision at relatively fast detection speeds to assist in textile industry quality control. The system consists of image acquisition hardware and image processing software. The software we developed uses data preprocessing techniques to break down raw images to smaller suitable sizes. Filtering is employed to denoise and enhance some features. To generalize and multiply the data to create robustness, we use data augmentation, which is followed by labeling where the defects in the images are labeled and tagged. Lastly, we utilize YOLOv4 for localization where the system is trained with weights of a pretrained model. Our software is deployed with the hardware that we designed to implement the detection system. The designed system shows strong performance in defect detection with precision of , and recall and scores of and , respectively. The detection speed is relatively fast at fps with a prediction speed of ms. Our system can automatically locate functional textile fabric defects with high confidence in real time.
NganHYPangGKYungNH.Automated fabric defect detection—a review. Image Vis Comput2011;
29: 442–458.
2.
KumarA.Computer-vision-based fabric defect detection: a survey. IEEE Tran Ind Electron2008;
55: 348–363.
3.
QuTZouLZhangQ, et al.
Defect detection on the fabric with complex texture via dual-scale over-complete dictionary. J Text Inst2016;
107: 743–756.
4.
WangTChenYQiaoM, et al.
A fast and robust convolutional neural network-based defect detection model in product quality control. Int J Adv Manu2018;
94: 3465–3471.
5.
WeimerDScholz-ReiterBShpitalniM.Design of deep convolutional neural network architectures for automated feature extraction in industrial inspection. CIRP Annals2016;
65: 417–420.
6.
Bodnarova A, Bennamoun M and Kubik K. Defect detection in textile materials based on aspects of the HVS. In: 1998 IEEE international conference on systems, man, and cybernetics (SMC'98 Conference Proceedings) (Cat No 98CH36216), San Diego, Ca, USA. 11–14 October 1998. IEEE. pp.4423–4428.
7.
NganHYPangGKYungNH.Motif-based defect detection for patterned fabric. Pattern Recognit2008;
41: 1878–1894.
8.
ZhuDPanRGaoW, et al.
Yarn-dyed fabric defect detection based on autocorrelation function and GLCM. Autex Res J2015;
15: 226–232.
9.
Latif-AmetAErtüzünAErçilA.An efficient method for texture defect detection: sub-band domain co-occurrence matrices. Image Vis Comput2000;
18: 543–553.
10.
ChanC-hPangGK.Fabric defect detection by Fourier analysis. IEEE Trans Ind Appl2000;
36: 1267–1276.
11.
TsaiD-MHuangT-Y.Automated surface inspection for statistical textures. Image Vis Comput2003;
21: 307–323.
Sari-Sarraf H and Goldard JS. Vision system for on-loom fabric inspection. In: 1998 IEEE annual textile, fiber and film industry technical conference (Cat No 98CH36246), Charlotte, NC, USA. 5–7 May 1998. IEEE. pp.8/1–810.
14.
YangXPangGYungN.Discriminative training approaches to fabric defect classification based on wavelet transform. Pattern Recognit2004;
37: 889–899.
15.
NganHYPangGKYungSP, et al.
Wavelet based methods on patterned fabric defect detection. Pattern Recognit2005;
38: 559–576.
16.
WoodEJ.Applying Fourier and associated transforms to pattern characterization in textiles. Text Res J1990;
60: 212–220.
17.
Guo C, Ma Q and Zhang L. Spatio-temporal saliency detection using phase spectrum of quaternion fourier transform. In: 2008 IEEE conference on computer vision and pattern recognition, Anchorage, AK, USA. 23–28 June 2008. IEEE. pp.1–8.
18.
Campell J, Hashim A and Murtagh F. Flaw detection in woven textile using space-dependent Fourier transform. Magee College, preprint: INFM-97-004. 16 May 1997.
19.
YapiDAlliliMSBaazizN.Automatic fabric defect detection using learning-based local textural distributions in the contourlet domain. IEEE Trans on Autom Sci Eng2017;
15: 1014–1026.
20.
Cohen FS, Fan Z and Attali S. Automated inspection of fabrics using textual models. IEEE Trans Pattern Anal Mach Intell 1991; 13: 803–808.
21.
AlliliMSBaazizNMejriM.Texture modeling using contourlets and finite mixtures of generalized Gaussian distributions and applications. IEEE Trans Multimedia2014;
16: 772–784.
22.
Long J, Shelhamer E and Darrell T. Fully convolutional networks for semantic segmentation. In: proceedings of the IEEE conference on computer vision and pattern recognition, Boston MA, USA. 7–12 June 2015. IEEE. pp.3131–3440.
JingJFMaHZhangHH.Automatic fabric defect detection using a deep convolutional neural network. Color Technol2019;
135: 213–223.
25.
Jun X, Wang J, Zhou J, et al. Fabric defect detection based on deep convolutional neural network using two-stage strategy. Text Res J 2020; 91: 130–142.
26.
Li F and Li F. Bag of tricks for fabric defect detection based on Cascade R-CNN. Text Res J 2020; 91: 599–612.
27.
JingJZhuoDZhangH, et al.
Fabric defect detection using the improved YOLOv3 model. J Eng Fibers Fabr2020;
15: 1558925020908268.
28.
Redmon J, Divvala S, Girshick R, et al. You only look once: unified, real-time object detection. In: proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, NV, USA. 27–30 June 2016. IEEE. pp.779–788.
29.
Neubeck A, and Van Gool L. Efficient non-maximum suppression. In: 18th international conference on pattern recognition (ICPR’06), Hong Kong, China. 20–24 August 2006. IEEE. pp.850–855.
30.
Redmon J, and Farhadi A. YOLO9000: better, faster, stronger. In: proceedings of IEEE conference on computer vision and pattern recognition, Honolulu, HI, USA. 21–26 July 2017. IEEE. pp.7263–7271.
31.
IoffeSSzegedyC. Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502031672015.
32.
Zhang Y, Zhang H and Huang TS. Collaborative and compressive high-resolution imaging. In: proceedings of the 21st international conference on pattern recognition (ICPR2012), Tsukuba, Japan. 11–15 November 2012. IEEE. pp.3062–3065.
33.
ChenYHanCWangN, et al. Revisiting feature alignment for one-stage object detection. arXiv preprint arXiv:1908015702019.
34.
BouveyronCGirardSSchmidC.High-dimensional data clustering. Comput Stat Data Anal2007;
52: 502–519.
35.
RedmonJFarhadiA. Yolov3: an incremental improvement. arXiv preprint arXiv:1804027672018.
36.
Lin T-Y, Dollar P, Girschick R, et al. Feature pyramid networks for object detection. In: proceedings of the IEEE conference on computer vision and pattern recognition, Honolulu, HI, USA. 21–26 July 2017. IEEE. pp.2117–2125.
37.
He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. In: proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, NV, USA. 27–30 June 2016. IEEE. pp.770–778.
38.
SrivastavaNHintonGKrizhevskyA, et al.
Dropout: a simple way to prevent neural networks from overfitting. Journal Mach Learn Res2014;
15: 1929–1958.
39.
BochkovskiyAWangC-YLiaoH-YM. YOLOv4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004109342020.
40.
Yun S, Han D, Oh SJ, et al. Cutmix: regularization strategy to train strong classifiers with localizable features. In: proceedings of IEEE international conference on computer vision, Seoul, Korea. 27 October–2 November 2019. IEEE. pp.6023–6032.
41.
Ghiasi G, Lin T-Y and Le QV. Dropblock: a regularization method for convolutional networks. In: Advances in neural information processing systems, Montreal, Canada. 2–8 December 2018. NIPS. pp.10727–1073.
42.
HeKZhangXRenS, et al.
Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell2015;
37: 1904–1916.
43.
Liu S, Qi L, Qin H, et al. Path aggregation network for instance segmentation. In: proceedings of the IEEE conference on computer vision and pattern recognition, Salt Lake City, UT, USA. 18–23 June 2018. IEEE. pp.8759–8768.
44.
OhGLeeSShinSY.Fast determination of textural periodicity using distance matching function. Pattern Recognit Lett1999;
20: 191–197.
45.
JingJYangPLiP, et al.
Supervised defect detection on textile fabrics via optimal Gabor filter. J Ind Text2014;
44: 40–57.
46.
GuptaG.Algorithm for image processing using improved median filter and comparison of mean, median and improved median filter. Int J Soft Comput (IJSCE)2011;
1: 304–311.
47.
SunTGabboujMNeuvoY.Center weighted median filters: some properties and their applications in image processing. Signal Process1994;
35: 213–229.
48.
DograABhallaP.Image sharpening by gaussian and Butterworth high pass filter. Biomed Pharmacol2014;
7: 707–713.
49.
PerezLWangJ. The effectiveness of data augmentation in image classification using deep learning. arXiv preprint arXiv:1712046212017.
50.
AntoniouAStorkeyAEdwardsH. Data augmentation generative adversarial networks. arXiv preprint arXiv:1711043402017.
51.
Cartucho J, Ventura R and Veloso M. Robust object recognition through symbiotic deep learning in mobile robots. In: 2018 IEEE/RSJ international conference on intelligent robots and systems (IROS), Madrid, Spain. 1–5 October 2018. IEEE. pp.2336–2341.
52.
Albahli S, Nida N, Irtaza A, et al. Melanoma lesion detection and segmentation using YOLOv4-DarkNet and active contour. IEEE Access 2020; 8: 198403–198414.
53.
Rezatofighi H, Tsoi N, Gwak J, et al. Generalized intersection over union: a metric and loss for bounding box regression. In: proceedings of the IEEE conference on computer vision and pattern recognition, Long Beach, CA, USA. 16–20 June 2019. IEEE. pp.658–666.
54.
Lin T-Y, Maire M, Belongie S, et al. Microsoft coco: common objects in context. In: 13th European conference on computer vision (ECCV2014), Zurich, Switzerland. 6–12 September 2014. Springer. pp.740–755.
55.
StojanovicRMitropulosPKoulamasC, et al.
Real-time vision-based system for textile fabric inspection. Real-Time Imaging2001;
7: 507–518.
56.
KuoC-FJLeeC-JTsaiC-C.Using a neural network to identify fabric defects in dynamic cloth inspection. Text Res J2003;
73: 238–244.
57.
KuoC-FJLeeC-J.A back-propagation neural network for recognizing fabric defects. Text Res J2003;
73: 147–151.
58.
ZhangYLuZLiJ.Fabric defect classification using radial basis function network. Pattern Recognit Lett2010;
31: 2033–2042.
59.
XieHWuZ.A robust fabric defect detection method based on improved RefineDet. Sensors2020;
20: 4260.
60.
HuGHuangJWangQ, et al.
Unsupervised fabric defect detection based on a deep convolutional generative adversarial network. Text Res J2020;
90: 247–270.
61.
LiuZZhangCLiC, et al.
Fabric defect recognition using optimized neural networks. J Eng Fibers Fabr2019;
14: 1558925019897396.
62.
Mei S, Wang Y and Wen G. Automatic fabric defect detection with multi-scale convolutional denoising autoencoder network model. Sensors 2018; 4: 1064.
63.
Zhou Q, Mei J, Zhang Q, et al. Semi-supervised fabric defect detection based on image reconstruction and density estimation. Text Res J 2020; 91: 962–972.
64.
Jing J, Wang Z, Ratsch M, et al. Mobile-Unet: efficient convolutional neural network for fabric defect detection. Tex Res J. Online first ahead of print 2020. 0040517530928604.
