The complex hairiness of slub yarns makes it challenging to accurately detect the yarn body and measure its appearance parameters. This paper proposes a method for measuring the parameters of continuous slub yarn images based on computer vision. First, overlapping slub yarn sequence images are captured using a specially designed image capture device. Then, an image stitching method based on normalized cross-correlation is proposed to remove the overlapping data from neighboring slub yarn images. To handle the complex hairiness around the slub yarn, an improved knowledge-enhanced contour detection method is used to accurately extract the backbone contour of the slub yarn. Finally, the extracted slub yarn contour is analyzed using such methods as frequency histograms and curve fitting. Contour detection results show that the proposed yarn contour detection method achieves better performance, with an optimal dataset scale of 0.930 and an optimal image scale of 0.931. The parameters of slub yarn measured using the proposed method are consistent with the production process settings. The experimental results demonstrate that the method can accurately detect slub yarn parameters, providing a basis for the appearance design and proofing of slub fabrics in textile enterprises.
GongRHWrightRM.Fancy yarns: Their manufacture and application.
Cambridge:
Woodhead, 2002.
2.
WuSLiJ, andYuC.Simulation of fiber arrangement in slub strands and twisting on the slub yarn with the finite element method. Text Res J2023;
93: 1445–1455.
3.
BarellaA.Law of critical yarn diameter and twist influence on yarn characteristics. Text Res J1950;
20: 249–258.
4.
PanRGaoWLiuJ, et al.
Recognition the parameters of slub-yarn based on image analysis. J Eng Fibers Fabr2011;
6: 25–30.
5.
JaganathanS.Characterization methods and physical properties of novelty yarn. MSc Thesis, North Carolina State University, USA, 2005.
6.
LiuJXieZGaoW, et al.
Automatic determination of slub yarn geometrical parameters based on an amended similarity-based clustering method. Text Res J2010;
80: 1075–1082.
7.
LiangJLuoJ.Determination on slub length for slubby yarn of ring bobbin. Appl Mech Mater2011;
52: 1970–1975.
LvHMaC.Partition slub yarn into slub parts and base parts. Adv Mater Res2011;
301: 251–256.
10.
El-KhalekAEl-BealyR, andEl-DeebA.A computer-based system for evaluation of slub yarn characteristics. J Text2014;
2014: 784516.
11.
EldessoukiMIbrahimS, andMilitkyJ.A dynamic and robust image processing based method for measuring the yarn diameter and its variation. Text Res J2014;
84: 1948–1960.
12.
LiZXiangJWangL, et al.
Measuring the geometrical parameters of slub yarn using a computer vision based image sequencing technique. Fibres Text East Eur2019;
27: 26–35.
13.
YuanRWJiangXM.Research on on-line detection technology for yarn evenness. Adv Mater Res2011;
301–303: 60–66.
14.
LiuJJiangHPanR, et al.
Evaluation of yarn evenness in fabric based on image processing. Text Res J2012;
82: 1026–1037.
15.
LiJZuoBWangC, et al.
A direct measurement method of yarn evenness based on machine vision. J Eng Fibers Fabr2015;
10: 155892501501000403.
16.
VajpayeePPanigrahyC, andKumarA.Medical image fusion by adaptive Gaussian PCNN and improved Roberts operator. Signal, Image Video Process2023;
17: 3565–3573.
17.
TianRSunGLiuX, et al.
Sobel edge detection based on weighted nuclear norm minimization image denoising. Electronics2021;
10: 655.
18.
BalochianSBaloochianH.Edge detection on noisy images using Prewitt operator and fractional order differentiation. Multimedia Tools Appl2022;
81: 9759–9770.
19.
CannyJ.A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell1986;
PAMI-8: 679–698.
20.
ColemanSAScotneyBW, andSuganthanS.Edge detecting for range data using Laplacian operators. IEEE Trans Image Process2010;
19: 2814–2824.
21.
BertasiusGShiJ, andTorresaniL. DeepEdge: A multi-scale bifurcated deep network for top-down contour detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), Boston, MA, USA, 7–12 June 2015, pp. 4380–4389. Piscataway, NJ: IEEE.
22.
XieSTuZ. Holistically-nested edge detection. In: Proceedings of the IEEE international conference on computer vision (ICCV), Santiago, Chile, 7–13 December 2015, pp. 1395–1403. Piscataway, NJ: IEEE.
23.
ShenWWangXWangY, et al. DeepContour: A deep convolutional feature learned by positive-sharing loss for contour detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), Boston, MA, USA, 7–12 June 2015, pp. 3982–3991. Piscataway, NJ: IEEE.
24.
YangHLiYYanX, et al.
ContourGAN: Image contour detection with generative adversarial network. Knowledge-Based Syst2019;
164: 21–28.
25.
LiuYChengM-MHuX, et al. Richer convolutional features for edge detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), Honolulu, HI, USA, 21–26 July 2017, pp. 3000–3009. Piscataway, NJ: IEEE.
26.
PomaXSRibaE, andSappaA. Dense extreme inception network: Towards a robust CNN model for edge detection. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision (WACV), Snowmass, CO, USA, 1–5 March 2020, pp. 1923–1932. Piscataway, NJ: IEEE.
27.
SoriaXSappaAHumananteP, et al.
Dense extreme inception network for edge detection. Pattern Recognit2023;
139: 109461.
28.
SuZLiuWYuZ, et al. Pixel difference networks for efficient edge detection. In: Proceedings of the IEEE/CVF international conference on computer vision (ICCV), Montreal, QC, Canada, 10–17 October 2021, pp. 5117–5127. Piscataway, NJ: IEEE.
29.
HuanLXueNZhengX, et al.
Unmixing convolutional features for crisp edge detection. IEEE Trans Pattern Anal Mach Intell2022;
44: 6602–6609.
30.
XianRXiongXPengH, et al.
Feature fusion method based on spiking neural convolutional network for edge detection. Pattern Recognit2024;
147: 110112.
31.
ZhangXLinC.Multi-decoding network with attention learning for edge detection. Neural Process Lett2023;
55: 4889–4906.
32.
ElharroussOHmamoucheYIdrissiAK, et al.
Refined edge detection with cascaded and high-resolution convolutional network. Pattern Recognit2023;
138: 109361.
33.
MuntarinaKMostafizRKhanomF, et al.
MultiResEdge: A deep learning-based edge detection approach. Intell Syst Appl2023;
20: 200274.
34.
ZhangXLinCLiF, et al.
LVP-net: A deep network of learning visual pathway for edge detection. Image Vision Comput2024;
147: 105078.
35.
YangWChenX-DWuW, et al.
Boosting deep unsupervised edge detection via segment anything model. IEEE Trans Ind Inf2024;
20: 8961–8971.
36.
CaldasPSousaFPereiraF, et al.
Automatic system for yarn quality analysis by image processing. J Braz Soc Mech Sci2022;
44: 565.
37.
SunYLiZPanR, et al.
Measurement of long yarn hair based on hairiness segmentation and hairiness tracking. J Text Inst2017;
108: 1271–1279.
38.
LiZPanRZhangJ, et al.
Measuring the unevenness of yarn apparent diameter from yarn sequence images. Meas Sci Technol2016;
27: 015404.
39.
LiZPanRWangJ, et al.
Real-time segmentation of yarn images based on an FCM algorithm and intensity gradient analysis. Fibres Text East Eur2016;
24: 45–50.
40.
LiZZhongPTangX, et al.
A new method to evaluate yarn appearance qualities based on machine vision and image processing. IEEE Access2020;
8: 30928–30937.
41.
WangLLuYPanR, et al.
Evaluation of yarn appearance on a blackboard based on image processing. Text Res J2021;
91: 2263–2271.
42.
RodriguesMPereiraF, andMachadoJ.Analysis of basic characteristics of textile yarn using image processing techniques. In: BurdukABatakoAMachadoJ, et al. (eds.) Advances in production.
Cham:
Springer, 2023, pp. 215–227.
43.
HaleemNBustreoM, andDel BueA. Online evaluation of textile yarn evenness using fast exposure imaging and image processing techniques. In: 2023 7th international conference on automation, control and robots (ICACR), Kuala Lumpur, Malaysia, 4–6 August 2023, pp. 68–72. Piscataway, NJ: IEEE.
44.
ZhangHZhuHYanK, et al.
Yarn apparent evenness detection based on L0 norm smoothing and the expectation maximization method. Text Res J2023;
93: 422–433.
45.
ZhangHChengSZhaoY, et al.
Measurement of yarn apparent evenness based on modified Canny edge detection. J Text Inst2024;
115: 600–606.
46.
XuCWangJTaoJ, et al.
A knowledge augmented deep learning method for vision-based yarn contour detection. J Manuf Syst2022;
63: 317–328.
