EUVIMEDOpdag EUVIMED
Open access · CC BY-NC-ND 4.0

An end‐to‐end steel surface defect detection approach via Swin transformer

Bo Tang, Zi‐Kai Song, Wei Sun, Xing‐Dong Wang

IET Image Processing · 2023-04 · 17 (5) · 1334-1345

DOI: 10.1049/ipr2.12715 ↗

At a glance

Journal article in IET Image Processing, published online on 2022-12-20. Written by Bo Tang and 3 co-authors. Cited 34 times so far (Crossref); 60 references. The full text is freely available (open access, CC BY-NC-ND 4.0). Funded by: National Natural Science Foundation of China.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Different from most current studies using convolutional neural network (CNN), a deep learning detection method for steel plate surface defects based on Transformer is researched. This paper presents a process, network structure and detection method for steel strip surface defect detection. A Swin Transformer was used to extract hierarchical features in the detection system. Then feature pyramid networks (FPN) was used to fuse the above features to form multi‐scale feature maps, and region proposal network (RPN) was adopted to generate the generate region of interest (ROI) of defects. Finally, the ROI head was used to generate defect category information and its precise location. Here, ablation experiments were conducted to explore the impact of different backbone networks and the number of stages of Swin Transformer and FPN on target detection performance to prove the rationality and efficiency of the network. On the NEU‐DET dataset, the proposed algorithm achieved 81.1% mAP, which is higher than that of classic CNN detection methods such as Faster R‐CNN, SSD, Yolo v3 and RepPoints.

Funding

  • National Natural Science Foundation of China

Cite

APA

Tang, B., Song, Z., Sun, W., & Wang, X. (2023). An end‐to‐end steel surface defect detection approach via Swin transformer. IET Image Processing, 17(5), 1334-1345. https://doi.org/10.1049/ipr2.12715

Vancouver

Tang B, Song Z, Sun W, Wang X. An end‐to‐end steel surface defect detection approach via Swin transformer. IET Image Processing. 2023;17(5):1334-1345. doi:10.1049/ipr2.12715

BibTeX
@article{Tang2023,
  author = {Tang, Bo and Song, Zi‐Kai and Sun, Wei and Wang, Xing‐Dong},
  title = {An end‐to‐end steel surface defect detection approach via Swin transformer},
  journal = {IET Image Processing},
  year = {2023},
  volume = {17},
  number = {5},
  pages = {1334--1345},
  doi = {10.1049/ipr2.12715}
}
Start for free →