EUVIMEDEUVIMED entdecken
Crossref

Fabric defect image generation method based on the dual-stage W-net generative adversarial network

Xuejuan Hu, Yifei Liang, Hengliang Wang, Yadan Tan, Shiqian Liu, Fudong Pan, Qingyang Wu, Zhengdi He

Textile Research Journal · 2024-07 · 94 (13-14) · 1543-1557

DOI: 10.1177/00405175241233942 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Textile Research Journal, online erschienen am 29.02.2024. Verfasst von Xuejuan Hu und 7 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 41 Literaturangaben. Gefördert von: Shenzhen Natural Science Foundation General Project, the Guangdong Provincial Key Areas Special Project, the Self-made Instrument Project of Shenzhen Technology University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Due to the intricate and diverse nature of textile defects, detecting them poses an exceptionally challenging task. In comparison with conventional defect detection methods, deep learning-based defect detection methods generally exhibit superior precision. However, utilizing deep learning for defect detection requires a substantial volume of training data, which can be particularly challenging to accumulate for textile flaws. To augment the fabric defect dataset and enhance fabric defect detection accuracy, we propose a fabric defect image generation method based on Pix2Pix generative adversarial network. This approach devises a novel dual-stage W-net generative adversarial network. By increasing the network depth, this model can effectively extract intricate textile image features, thereby enhancing its ability to expand information sharing capacity. The dual-stage W-net generative adversarial network allows generating desired defects on defect-free textile images. We conduct quality assessment of the generated fabric defect images resulting in peak signal-to-noise ratio and structural similarity values exceeding 30 and 0.930, respectively, and a learned perceptual image patch similarity value no greater than 0.085, demonstrating the effectiveness of fabric defect data augmentation. The effectiveness of dual-stage W-net generative adversarial network is established through multiple comparative experiments evaluating the generated images. By examining the detection performance before and after data augmentation, the results demonstrate that mean average precision improves by 6.13% and 14.57% on YOLO V5 and faster recurrent convolutional neural networks detection models, respectively.

Förderung

  • Shenzhen Natural Science Foundation General Project
  • the Guangdong Provincial Key Areas Special Project
  • the Self-made Instrument Project of Shenzhen Technology University
  • Guangdong provincial demonstration base project for joint cultivation of postgraduate students, “Shenzhen Libang Precision Instrument Co., Ltd.”
  • Shenzhen Pingshan District Science and technology innovation special supporting project

Zitieren

APA

Hu, X., Liang, Y., Wang, H., Tan, Y., Liu, S., Pan, F., Wu, Q., & He, Z. (2024). Fabric defect image generation method based on the dual-stage W-net generative adversarial network. Textile Research Journal, 94(13-14), 1543-1557. https://doi.org/10.1177/00405175241233942

Vancouver

Hu X, Liang Y, Wang H, Tan Y, Liu S, Pan F, et al. Fabric defect image generation method based on the dual-stage W-net generative adversarial network. Textile Research Journal. 2024;94(13-14):1543-1557. doi:10.1177/00405175241233942

BibTeX
@article{Hu2024,
  author = {Hu, Xuejuan and Liang, Yifei and Wang, Hengliang and Tan, Yadan and Liu, Shiqian and Pan, Fudong and Wu, Qingyang and He, Zhengdi},
  title = {Fabric defect image generation method based on the dual-stage W-net generative adversarial network},
  journal = {Textile Research Journal},
  year = {2024},
  volume = {94},
  number = {13-14},
  pages = {1543--1557},
  doi = {10.1177/00405175241233942}
}
Kostenlos starten →