EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FDTransUnet: An aluminum surface defect segmentation model based on feature differentiation

Mingzhu Tang iD, Wencheng Wang

PLOS ONE · 19.03.2025 · 20 (3) · e0320060

DOI: 10.1371/journal.pone.0320060 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 19.03.2025. Verfasst von Mingzhu Tang und 1 weiteren Autor:innen. Beteiligte Einrichtung: College of Mechanical and Control Engineering, Guilin University of Technology, Guilin, China. Hauptthemen laut MEDLINE: Aluminum, Models, Theoretical. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aiming at the current problems in the field of industrial defect segmentation, such as difficulty of obtaining a large number of defect samples, low recognition accuracy and lack of segmentation accuracy, a surface defect segmentation model for aluminum based on feature differentiation is proposed: FDTransUnet. First, the limited defective samples are effectively expanded by the feature differentiation data augmentation strategy to alleviate the overfitting problem caused by the insufficient sample. Second, the Transformer architecture is added by improving the U-net network, and the improved network combines the global self-attention mechanism of the Transformer and the hierarchical structure of the U-net, which can effectively extract the local and global information in the defect sample. Finally, a composite loss function is constructed to address the problem of unbalanced foreground and background sizes of defective samples and to improve segmentation accuracy. The experimental results show that FDTransUnet achieves 94.5% MPA and 89.7% Dice coefficient on the aluminum surface defect dataset. In the final generalization experiment, FDTransUnet is validated with other mainstream segmentation models on the steel surface defect dataset, and the experiment proves that the segmentation model has good generalization performance and robustness, and can be applied to different scenarios of industrial inspection.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AluminumModels, TheoreticalAlgorithmsSurface PropertiesNeural Networks, ComputerSteel

Substanzen

AluminumSteel

Autor:innen und Institutionen

  • College of Mechanical and Control Engineering, Guilin University of Technology, Guilin, China.
  • Key Laboratory of Advanced Manufacturing and Automation Technology Guilin University of Technology, Education Department of Guangxi Zhuang Autonomous Region, Guilin, China.

ORCID-Profile: Mingzhu Tang

Zitieren

APA

Tang, M., & Wang, W. (2025). FDTransUnet: An aluminum surface defect segmentation model based on feature differentiation. PLOS ONE, 20(3), e0320060. https://doi.org/10.1371/journal.pone.0320060

Vancouver

Tang M, Wang W. FDTransUnet: An aluminum surface defect segmentation model based on feature differentiation. PLOS ONE. 2025;20(3):e0320060. doi:10.1371/journal.pone.0320060

BibTeX
@article{Tang2025,
  author = {Tang, Mingzhu and Wang, Wencheng},
  title = {FDTransUnet: An aluminum surface defect segmentation model based on feature differentiation},
  journal = {PLOS ONE},
  year = {2025},
  volume = {20},
  number = {3},
  pages = {e0320060},
  doi = {10.1371/journal.pone.0320060}
}
Kostenlos starten →