EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Few-Shot Steel Surface Defect Generation Method Based on Diffusion Models

Hongjie Li iD, Yang Liu, Chuni Liu iD, Hongxuan Pang, Ke Xu iD

Sensors · 12.05.2025 · 25 (10) · 3038

DOI: 10.3390/s25103038 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 12.05.2025. Verfasst von Hongjie Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: Collaborative Innovation Center of Steel Technology, University of Science and Technology Beijing, Beijing 100083, China. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Beijing Science and Technology Planning Project, Key Technologies Research and Development Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Few-shot steel surface defect generation remains challenging due to the limited availability of training samples and the complex visual characteristics of industrial defects. Traditional data augmentation techniques often fail to capture the diverse manifestations of defects, resulting in suboptimal detection performance. While existing stable diffusion models possess robust generative capabilities, they encounter domain knowledge transfer limitations when applied to industrial settings. To address these constraints, stable industrial defect generation (stableIDG) is proposed, which enhances stable diffusion through three key improvements: (1) fine-tuning with low-rank embedding adaptation to accommodate steel surface defect generation; (2) implementation of personalized identifiers associated with defect regions to prevent malformation during generation; and (3) development of a mask-guided defect learning mechanism that directs network attention toward critical defect regions, thereby enhancing the fidelity of generated details. The method was validated on a newly constructed Medium and Heavy Plate Surface Defect Dataset (MHPSD) from a real industrial environment. Experiments demonstrated that stableIDG achieved better image generation quality compared to existing methods, such as textual inversion. Furthermore, when the generated samples were used for data augmentation, the detection network performance was effectively enhanced. Detection recall significantly improved for both defect classes, increasing from 0.656 to 0.908 for Inclusion defects and from 0.86 to 0.986 for Foreign Object Embedding defects. These results demonstrate the effectiveness of the proposed method for industrial defect detection in data-scarce scenarios.

Schlagwörter

Stichwörter der Autor:innen

data augmentationdeep learningdefect detectiondiffusion modelimage generationindustrial inspectionsurface defects

Autor:innen und Institutionen

  • Collaborative Innovation Center of Steel Technology, University of Science and Technology Beijing, Beijing 100083, China.
  • Hebei Puyang Iron & Steel Co., Ltd., Handan 056305, China.

ORCID-Profile: Hongjie Li, Chuni Liu, Ke Xu

Förderung

  • Beijing Science and Technology Planning Project
  • Key Technologies Research and Development Program of China

Zitieren

APA

Li, H., Liu, Y., Liu, C., Pang, H., & Xu, K. (2025). A Few-Shot Steel Surface Defect Generation Method Based on Diffusion Models. Sensors, 25(10), 3038. https://doi.org/10.3390/s25103038

Vancouver

Li H, Liu Y, Liu C, Pang H, Xu K. A Few-Shot Steel Surface Defect Generation Method Based on Diffusion Models. Sensors. 2025;25(10):3038. doi:10.3390/s25103038

BibTeX
@article{Li2025,
  author = {Li, Hongjie and Liu, Yang and Liu, Chuni and Pang, Hongxuan and Xu, Ke},
  title = {A Few-Shot Steel Surface Defect Generation Method Based on Diffusion Models},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {10},
  pages = {3038},
  doi = {10.3390/s25103038}
}
Kostenlos starten →