Three-dimensional (3D) textile-based garment prototyping, widely adopted in the apparel and textile industry, enhances cost efficiency, work productivity, and seamless communication via visual prototyping. Neural network-based 3D textile digitization has the potential to streamline manufacturing processes by negating the need for traditional physical property (PT) measurements. However, a research gap exists concerning the accuracy of the technology and its applicability to advanced functional apparel manufacturing. The primary research question is to investigate how variations in digitized physical properties obtained from PT measurements and artificial intelligence (AI)-based textile digitization impact the accuracy of a fabric’s mechanical representation. In this study, we aimed to evaluate AI-based textile digitization accuracy using a drape test method. The drape coefficient (DC) analysis revealed that the PT-based simulated DC exhibited a normalized mean absolute error (NMAE) ranging from 2% to 11%, while the AI-based simulated DC showed a range of 3–51%. Notably, for the samples, except those with very limp or very stiff fabric samples, the AI-based simulation exhibited a NMAE within 3–15%.
Hwang ShinS-JLeeH.The use of 3D virtual fitting technology: comparison between sourcing agents contractors and domestic suppliers in the apparel industry. Int J Fash Des Technol Educ2020;
13: 300–307.
2.
YounSMathurKKnowlesC, et al. Simulation-based prediction model to optimize contact pressure of knitted fabrics for wearable garments. In: Ahram T and Taiar R (eds) 9th international conference on human interaction and emerging technologies - artificial intelligence and future applications, Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland, 13–15 April 2023, vol. 70, issue no. 70, pp. 198–203. New York: AHFE International. DOI: 10.54941/ahfe1002922.
Rodriguez‐PardoCPrieto‐MartinMCasasD, et al.
How will it drape like? Capturing fabric mechanics from depth images. Comput Graph Forum2023;
42: 149–160.
5.
HeKZhangXRenS, et al. Deep residual learning for image recognition. In: Song H, Xiang Y, Jegelka S, et al. (eds) proceedings of the IEEE conference on computer vision and pattern recognition. Las Vegas, NV, USA, 27–30 June 2016, pp. 770–778. New York: Institute of Electrical and Electronic Engineers (IEEE).
6.
GarcesEArellanoVRodriguez-PardoC, et al.
Towards material digitization with a dual-scale optical system. ACM Trans Graph2023;
42: 1–13.
7.
GarcesERodriguez-PardoC.Generating a material property map of a computer model of a material based on a set of micro-scale images. Patent 2023/0145496 A1, USA, 11 May 2023.
8.
MozafaryVPayvandyPRezaeianM.A novel approach for simulation of curling behavior of knitted fabric based on mass spring model. J Text Inst2018;
109: 1620–1641.
9.
BSI - BS 5058:1973. Method for the assessment of drape of fabrics.
10.
YuZZhongYGongRH, et al.
New indicators on fabric drape evaluation based on three-dimensional model. Text Res J2020;
90: 1291–1300.
11.
BaraffDWitkinA. Large steps in cloth simulation. In: proceedings of the 25th annual conference on computer graphics and interactive techniques (SIGGRAPH ‘98), Orlando, FL, USA, 19–24 July 1998, pp. 43–54. Not Known: ACM Press.
12.
MozafaryVPayvandyP.A novel method based on loop shape for simulating knitted fabric using mass spring model. Fibers Polym2017;
18: 533–541.
13.
JuEChoiMG.Estimating cloth simulation parameters from a static drape using neural networks. IEEE Access2020;
8: 195113–195121.
14.
KimHJYounSChoiJ, et al.
Indexing surface smoothness and fiber softness by sound frequency analysis for textile clustering and classification. Text Res J2021;
91: 200–218.
15.
HesLUnmarRIranahSR.Fashion requirements influencing sensorial and thermal comfort of clothing. J Text Eng Fashion Technol2022;
8: 173–176.
16.
RaafiSkMArjuSNAsaduzzamanMd, et al.
Eco-friendly scouring of cotton knit fabrics with enzyme and soapnut: an alternative to conventional NaOH and synthetic surfactant based scouring. Heliyon2023;
9: e15236.
17.
ShinBYuDLeeS, et al.
Development of a simple drape measurement method for 3D virtualization. J Korean Soc Cloth Text2021;
45: 881–891.
Youn S, Knowles CG, Mills AC and Mathur K (10 Feb 2024):
Comparative study of physical and virtual fabric parameters: physical versus virtual drape test using commercial 3D garment software. The Journal of The Textile Institute. DOI: 10.1080/00405000.2024.2314273.
JaouadiMMsahliSSakliF.Contribution to measurement of real yarn diameter. J Text Inst2009;
100: 158–164.
24.
NohutSTascanMAkgobekO, et al.
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: 155892501501000218.
25.
SperlGSánchez-BanderasRMLiM, et al.
Estimation of yarn-level simulation models for production fabrics. ACM Trans Graph2022;
41: 1–15.
26.
JamshaidHRajputAWZahidB, et al.
Comparison of functional properties of woven and knitted denim fabrics. Ind Textila2020;
71: 3–7.
27.
LamARahejaAGovindarajM. Neural network models for fabric drape prediction. In: 2004 IEEE international joint conference on neural networks (IEEE Cat. No.04CH37541), 25–29 July 2004, pp. 2925–2929. Budapest, Hungary: IEEE.
28.
Rodriguez-PardoCKazatzisKLopez-MorenoJ, et al.
NeuBTF: neural fields for BTF encoding and transfer. Comput Graph2023;
114: 239–246.
