EUVIMEDEUVIMED entdecken
Crossref

Improved generative adversarial networks for denoising fabric defect images

Xudong Hu, Tao Wang, Bo Yu, Ning Dai, Chunya Shen, Yanhong Yuan

Textile Research Journal · 2025-08 · 95 (15-16) · 1877-1901

DOI: 10.1177/00405175241306996 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Textile Research Journal, online erschienen am 23.01.2025. Verfasst von Xudong Hu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 36 Literaturangaben. Gefördert von: The Science and Technology Program of Zhejiang Province, China, The Zhejiang Sci-Tech University Research Start-up Fund, China, Zhejiang Provincial Department of Education Scientific Research Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In order to solve the problems of noise, blurring, and loss of detail in fabric defect images due to camera location and factory environments, a fabric defect image denoising method based on improved generative adversarial network (GAN) is proposed. A mathematical model is developed to simulate the noisy images of fabric blemishes in a real factory environment. GAN, as a deep learning method widely used in the field of computer vision, generates high-quality data samples through the competition between generators and discriminators. In this study, the traditional GAN is improved by introducing multiple loss terms and adopting a new adaptive weighting strategy in order to make the denoised image closer to the original clear image while better preserving the structural and detailed features of the image. In addition, the network structure is improved by introducing a multiscale discriminator, a convolutional block attention module (CBAM) and a residual network to capture feature information at different spatial scales more effectively and to promote the propagation of low-level features. The experimental results show that the method can effectively remove fabric defective image noise, and its subjective effect and objective indexes are better than similar algorithms. The research results are of great value to quality inspectors, related researchers, and image denoising technology professionals in the textile industry. These results help to improve the efficiency and accuracy of fabric defect detection and image denoising processing, thus promoting the development of related technologies.

Förderung

  • The Science and Technology Program of Zhejiang Province, China
  • The Zhejiang Sci-Tech University Research Start-up Fund, China
  • Zhejiang Provincial Department of Education Scientific Research Project

Zitieren

APA

Hu, X., Wang, T., Yu, B., Dai, N., Shen, C., & Yuan, Y. (2025). Improved generative adversarial networks for denoising fabric defect images. Textile Research Journal, 95(15-16), 1877-1901. https://doi.org/10.1177/00405175241306996

Vancouver

Hu X, Wang T, Yu B, Dai N, Shen C, Yuan Y. Improved generative adversarial networks for denoising fabric defect images. Textile Research Journal. 2025;95(15-16):1877-1901. doi:10.1177/00405175241306996

BibTeX
@article{Hu2025,
  author = {Hu, Xudong and Wang, Tao and Yu, Bo and Dai, Ning and Shen, Chunya and Yuan, Yanhong},
  title = {Improved generative adversarial networks for denoising fabric defect images},
  journal = {Textile Research Journal},
  year = {2025},
  volume = {95},
  number = {15-16},
  pages = {1877--1901},
  doi = {10.1177/00405175241306996}
}
Kostenlos starten →