With the growing demand for nonwoven materials in high-end applications, traditional offline basis-weight measurements interrupt continuous production, and in-line weight-detection systems on carding machines only provide coarse, localized weight profiles (typically at centimeter-scale resolution), and cannot resolve fiber- or pore-level distribution uniformity. This paper proposes an online quality-inspection method for nonwoven fiber webs using machine vision and deep learning. High-resolution images captured on a bespoke inspection platform are preprocessed via wavelet transforms and image-enhancement techniques. A convolutional neural network regression model then estimates web basis weight in real time. To quantify fiber-distribution uniformity, this paper introduces a porosity-based metric and demonstrates that its coefficient of variation (CV) correlates strongly with the CV of measured web basis weight. The proposed approach delivers data-driven support for real-time adjustment of carding-machine process parameters, thereby overcoming the technical challenge of online uniformity monitoring in high-end nonwoven fabric production.
WenSWLiTS.An identification system for classifying nonwoven quality. Appl Mech Mate, 2012,
241-244(241-244):466–469.
2.
GloyYSGriesT. Non-destructive testing of fabric weight in the weaving process. In: Proceedings of the 13th International Symposium on the Nondestructive Characterization of Materials, 2013; vol.
19(4).
3.
HouWMWangX.Uniformity detection of acetate fiber web based on digital image processing. J Ind Text2017;
35(02): 37–44.
4.
XuB.Measurement of pore characteristics in nonwoven fabrics using image analysis. Cloth Text Res J1996;
14(1): 81–88.
5.
VictorV SSchmeißerALeitteH, et al. Machine learning for optimizing the homogeneity of spun-bond nonwovens. 2025; pp. 91–112.
6.
KohelLZengX.Digital image analysis to determine pore size distribution of nonwoven fabrics. Proceedings IEEE CESA, 2006, vol.
1, pp. 145–149.
7.
JahanzebSSiddiqueSH.Porosity and fiber orientation of banana fiber nonwoven webs using image analysis technique. J Nat Fibers2022;
19(13): 6056–6073.
8.
AydilekAHOguzSH.Digital image analysis to determine pore opening size distribution of nonwoven geotextiles. J Comput Civ Eng2002;
16(4): 280–290.
9.
KahramanYDurmuşoğluA.Deep learning-based fabric defect detection: A review. Text Res J2023;
93(5–6): 1485–1503.
10.
GültekinEÇelikHİ.Predicting air permeability and porosity of nonwovens with image processing and artificial intelligence methods. J Text Inst2020;
111(11): 1641–1651.
11.
NohutSTascanM.Estimation of areal weight, grab tensile strength, and elongation at break of PP spunbond nonwovens using digital image analysis and artificial neural networks. J Eng Fibers Fabr2015;
10(2): 155–163.
12.
LienHCLiuCH.A method of inspecting non-woven basis weight using the exponential law of absorption and image processing. Text Res J2006;
76(7): 547–558.
13.
ChhabraR.Nonwoven uniformity—Measurements using image analysis. Int Nonwovens J2003;
12(1): 43–50.
14.
LiuYY.Research on cloth defect detection method based on deep learning[D]. Harbin: Harbin Institute of Technology,2020.
15.
ZhangQPeiHL.Design of machine vision inspection system for stains on the surface of nonwoven fabrics[J]. J South China Univ Technol (Nat Sci Ed)2012;
4z0(3): 81–87.
16.
ZhaoY, et al.
A visual long-short-term memory based integrated CNN model for fabric defect image classification. Neurocomputing380 (2020): 259–270.
17.
JeongSHKimSH.The evaluation of evenness of nonwovens using image analysis method. Fibers Polym2001;
2: 164–170.
18.
LiangZJDengH.Uniformity analysis of organic/inorganic hybrid fiber web based on image processing. China Text Leader2019; 1: 81–84.
19.
YanZBreseeRR.Characterizing nonwoven-web structure by using image-analysis techniques. Part V: analysis of shot in meltblown webs. J Text Inst1998;
89(2): 320–336.
20.
Abbas Gholipourg HadimMMailahM. Porosity and pore area determination of hollow fiber membrane incorporating digital image processing. In Recent Advances in Mechanics and Mechanical Engineering, Proceedings of the 6th International Conference on Fluid Mechanics and Heat & Mass Transfer (FLUIDSHEAT’15), Proceedings of the 1st International Conference on Mechanical and Transportation Engineering (ICMTE’15), Kuala Lumpur, Malaysia, 2015, pp. 23–25.
21.
JunXWangJZhouJ, et al.
Fabric defect detection based on a deep convolutional neural network using a two-stage strategy. Text Res J2021;
91: 130–142.
22.
JingJFWangZZhouJ, et al.
Mobile-UNet: An efficient convolutional neural network for fabric defect detection. Text Res J2022;
92(1–2): 30–42.
23.
YangYS. Warp knitted fabric defect detection based on digital image processing. PhD Thesis, China University of Geosciences (Beijing), 2021.
24.
WangJZhangW.Predicting bond qualities of fabric composites after wash and dry wash based on principal-BP neural network model. Text Res J2007;
77(3): 142–150.
25.
LiuYY. Research on cloth defect detection method based on deep learning. PhD Thesis, Harbin Institute of Technology, 2020.
26.
AndrewsHCPrattWK.Computer Techniques in Image Processing.
New York:
Academic Press, 1970.
27.
SonkaMHlavacV.Image Processing, Analysis and Machine Vision.
Berlin:
Springer, 2013.
28.
LiYSZhangJB.Grayscale video traffic image edge detection based on CNN technology. Transp Comput2005;
23(4): 28–31.
29.
HeWJ. Noise analysis and image processing of CMOS image sensor. PhD Thesis, Huazhong University of Science and Technology, 2011.
30.
LewisASKnowlesG.Image compression using the 2-D wavelet transform. IEEE Trans Image Process1992;
1(2): 244–250.
31.
LiangZJ.Analysis and research on the fiber distribution of hybrid fiber webs based on image processing. PhD thesis, Tianjin Polytechnic University, 2019.
32.
KingmaDPBaJ. Adam: A method for stochastic optimization.“arXiv preprint arXiv:1412.6980 (2014).
33.
WangQMaLZ.Preservation of image features during image binarization. J Comput Aided Des Grap2000;
12(10): 746–750.
34.
JinHLiuF.Discussion on the solution to the uniformity problem of polypropylene spunbond nonwoven fabrics. J Ind Text2013;
31(3): 37–39.
35.
ChenJXiaoP.Identification and statistical study of pores in composite optical microscopy images based on neural network. Meas Control Technol2024;
43(03): 22–27+69.
36.
ImrithMKUnmarR.Determination of knitted fabric porosity using digital imaging techniques. Adv Mater Sci Eng2016;
1. DOI: 10.1155/2016/6470351
37.
MalcolmAALeongHY.Image segmentation and analysis for porosity measurement. J Mater Process Technol2007;
192: 391–396.
38.
TuranRBOkurA.Predicting the intra-yarn porosity by image analysis method. Text Res J2012;
82(16): 1720–1728.
