During spinning, knitting and weaving processes, the yarn apparent evenness is an important factor, which determines the quality of subsequent spinning production and fabric performance. This paper presents a powerful method which is based on L0 norm smoothing and the expectation maximization method to detect the yarn apparent evenness. The L0 norm smoothing method is first applied to remove the noise and enhance the yarn apparent evenness diameter features. Then, the expectation maximization method and the morphological opening operation were used to obtain the yarn evenness. Finally, we calculated the yarn apparent evenness diameter and the coefficient of variation of the evenness of the yarn apparent diameter. Compared with the capacitive evenness testers, the Otsu detection method and the fuzzy C-means detection method, our method can accurately detect the yarn apparent evenness better than the selected state-of-the-art methods.
ChiKPanRLiuJ, et al. Primary discussion on detection of yarn evenness based on digital image processing.J Text Res2012;
33: 19–24.
2.
LiangZXuBChiZ, et al.
Intelligent characterization and evaluation of yarn surface appearance using saliency map analysis, wavelet transform and fuzzy ARTMAP neural network.Exp Syst Appl2012;
39: 4201–4212.
3.
JainAKDasDKRayPK.A microprocessor-based system for obtaining variance-length curves of jute yarns.Text Res J1985;
55: 372–376.
4.
Guo-shengX. The application of photoelectric inspecting technique in yarn defect test. In: 2010 2nd International Conference on Signal Processing Systems. IEEE, 2010, 1: V1-276–V1-279.
5.
CarvalhoVHCardosoPJVasconcelosRM, et al. Optical yarn hairiness measurement system. In: 2007 5th IEEE International Conference on Industrial Informatics. IEEE, 2007, 1: 359–364.
6.
LiGAkankwasaNTZhaoQ, et al.
A novel system for yarn cross-section analysis based on dual orthogonal CCD sensors.J Nat Fibers2019;
16: 114–125.
7.
ZhouBWangHWangK, et al.
Nondestructive test technology research for yarn linear density unevenness.Autex Res J. Epub ahead of print 5 December 2021. https://doi.org/10.2478/aut-2021-0051
8.
PanQChenMHuY, et al.
System design for evenness measurement of raw silk.Fibres Text Eastern Europe2018;
1: 21–24.
9.
ChiKPanRLiuJ, et al. Primary discussion on detection of yarn evenness based on digital image processing.J Text Res2012;
33: 19–24.
10.
LiBLiZPanR, et al. Sequential image measurement method for yarn evenness.J Text Res2016;
37: 26–31.
11.
WangLXuBGaoW.3D Measurement of yarn hairiness via multi-perspective images.Opt Eng2018;
57: 025103.
12.
WangLXuBGaoW.Multi-perspective measurement of yarn hairiness using mirrored images.Text Res J2018;
88: 621–629.
13.
OzkayaYAAcarMJacksonM.Digital image processing and illumination techniques for yarn characterization.J Electron Imaging2005;
14: 23–47.
14.
ZhongPKangZHanS, et al.
Evaluation method for yarn diameter unevenness based on image sequence processing.Text Res J2015;
85: 369–379.
15.
WangLLuYPanR, et al.
Evaluation of yarn appearance on a blackboard based on image processing.Text Res J2021; 91(19–20). 004051752110028.
16.
LiZPanRZhangJ, et al.
Measuring the unevenness of yarn apparent diameter from yarn sequence images.Measurem Sci Technol2015;
27: 015404.
17.
ZhangHYanKLiP, et al. Design of yarn quality detection system based on machine vision.Laser Optoelectron Progr2019;
56: 161504.
18.
LiSYXuBGFuH, et al.
A two-scale attention model for intelligent evaluation of yarn surface qualities with computer vision.J Text Inst2018;
109: 798–812.
19.
El-GeiheiniAElKatebSAbdel-HamiedMR.Estimation of yarn’s coefficient of mass variation utilizing artificial intelligence techniques.TBIS2020;
2020: 521–528.
20.
HaleemNBustreoMDel BueA.A computer vision based online quality control system for textile yarns. Comput Indust2021;
133: 103550.
21.
LiBLiZPanR, et al. Measurement of yarn evenness using sequence images.J Text Res2016;
37: 26–31.
22.
MiaoJZhouXHuangTZ.Local segmentation of images using an improved fuzzy C-means clustering algorithm based on self-adaptive dictionary learning.Appl Soft Comput2020;
91: 106200.
23.
OtsuN.A threshold selection method from graylevel histograms.IEEE Trans Syst Man Cybern1979;
9: 62–66.
24.
ChiKPanRLiuJ, et al. Primary discussion on detection of yarn evenness based on digital image processing.J Text Res2012;
33: 19–24.
25.
RajPRAGeorgeA. FCM and Otsu’s thresholding based glaucoma detection and its analysis using fundus images. In: 2019 2nd International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT). IEEE, 2019, 1: 753–757.
26.
XuLLuCXuY, et al. Image smoothing via L0 gradient minimization. In: Proceedings of the 2011 SIGGRAPH Asia Conference. 2011: 1–12.
27.
ShibuDSPriyadharsiniSS.Multimodal medical image fusion using L0 gradient smoothing with sparse representation.Int J Imaging Syst Technol2021; 31(4): 2249–2266.
28.
WuYYangX, andChanKL. Unsupervised color image segmentation based on Gaussian mixture model. In: Fourth International Conference on Information, Communications and Signal Processing. IEEE, 2003.
29.
SegolNNadlerB. Improved convergence guarantees for learning Gaussian mixture models by EM and gradient EM. Electronic Journal of Statistics 2021; 15(2): 4510–4544.
30.
KasimFABPhengHSNordinSZB, et al. Gaussian mixture model – expectation maximization algorithm for brain images. In: 2021 2nd International Conference on Artificial Intelligence and Data Sciences (AiDAS). IEEE, 2021: 1–5.
