EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ResNet-SE-CBAM Siamese Networks for Few-Shot and Imbalanced PCB Defect Classification

Chao-Hsiang Hsiao iD, Huan-Che Su, Yin-Tien Wang iD, Min-Jie Hsu, Chen-Chien Hsu iD

Sensors · 07.07.2025 · 25 (13) · 4233

DOI: 10.3390/s25134233 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 07.07.2025. Verfasst von Chao-Hsiang Hsiao und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Information Engineering, Tamkang University, New Taipei City 251301, Taiwan. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science and Technology Council, Taiwan (ROC).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Defect detection in mass production lines often involves small and imbalanced datasets, necessitating the use of few-shot learning methods. Traditional deep learning-based approaches typically rely on large datasets, limiting their applicability in real-world scenarios. This study explores few-shot learning models for detecting product defects using limited data, enhancing model generalization and stability. Unlike previous deep learning models that require extensive datasets, our approach effectively performs defect detection with minimal data. We propose a Siamese network that integrates Residual blocks, Squeeze and Excitation blocks, and Convolution Block Attention Modules (ResNet-SE-CBAM Siamese network) for feature extraction, optimized through triplet loss for embedding learning. The ResNet-SE-CBAM Siamese network incorporates two primary features: attention mechanisms and metric learning. The recently developed attention mechanisms enhance the convolutional neural network operations and significantly improve feature extraction performance. Meanwhile, metric learning allows for the addition or removal of feature classes without the need to retrain the model, improving its applicability in industrial production lines with limited defect samples. To further improve training efficiency with imbalanced datasets, we introduce a sample selection method based on the Structural Similarity Index Measure (SSIM). Additionally, a high defect rate training strategy is utilized to reduce the False Negative Rate (FNR) and ensure no missed defect detections. At the classification stage, a K-Nearest Neighbor (KNN) classifier is employed to mitigate overfitting risks and enhance stability in few-shot conditions. The experimental results demonstrate that with a good-to-defect ratio of 20:40, the proposed system achieves a classification accuracy of 94% and an FNR of 2%. Furthermore, when the number of defective samples increases to 80, the system achieves zero false negatives (FNR = 0%). The proposed metric learning approach outperforms traditional deep learning models, such as parametric-based YOLO series models in defect detection, achieving higher accuracy and lower miss rates, highlighting its potential for high-reliability industrial deployment.

Schlagwörter

Stichwörter der Autor:innen

Automatic Optical InspectionSiamese networksdefect detectionfew-shot learningimbalanced datasets

Autor:innen und Institutionen

  • Department of Computer Science and Information Engineering, Tamkang University, New Taipei City 251301, Taiwan.
  • Department of Mechanical and Electro-Mechanical Engineering, Tamkang University, New Taipei City 251301, Taiwan.
  • Department of Artificial Intelligence, Tamkang University, New Taipei City 251301, Taiwan.
  • Innodisk Corporation, New Taipei City 221006, Taiwan.
  • Department of Electrical Engineering, National Taiwan Normal University, Taipei 10601, Taiwan.

ORCID-Profile: Chao-Hsiang Hsiao, Yin-Tien Wang, Chen-Chien Hsu

Förderung

  • National Science and Technology Council, Taiwan (ROC)

Zitieren

APA

Hsiao, C. H., Su, H. C., Wang, Y. T., Hsu, M. J., & Hsu, C. C. (2025). ResNet-SE-CBAM Siamese Networks for Few-Shot and Imbalanced PCB Defect Classification. Sensors, 25(13), 4233. https://doi.org/10.3390/s25134233

Vancouver

Hsiao CH, Su HC, Wang YT, Hsu MJ, Hsu CC. ResNet-SE-CBAM Siamese Networks for Few-Shot and Imbalanced PCB Defect Classification. Sensors. 2025;25(13):4233. doi:10.3390/s25134233

BibTeX
@article{Hsiao2025,
  author = {Hsiao, Chao-Hsiang and Su, Huan-Che and Wang, Yin-Tien and Hsu, Min-Jie and Hsu, Chen-Chien},
  title = {ResNet-SE-CBAM Siamese Networks for Few-Shot and Imbalanced PCB Defect Classification},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {13},
  pages = {4233},
  doi = {10.3390/s25134233}
}
Kostenlos starten →