EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Scanning electron microscopy noise classification using deep learning

Kevin Mogere Nyaburi, Surya Kamal, Richard K Hailstone

Micron · 2027-02 · 209 · 104137

DOI: 10.1016/j.micron.2026.104137 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Micron, 2027-02. Verfasst von Kevin Mogere Nyaburi und 2 weiteren Autor:innen. Beteiligte Einrichtung: Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology, 54 Lomb Memorial Drive, Rochester, 14623, NY, United States. Electr…. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Noise plays a critical role in determining the performance and quantitative accuracy of imaging using a scanning electron microscope (SEM). In existing SEM literature, SEM noise is often assumed to follow Gaussian or Poisson statistics. However, in practice, true statistical behavior can vary depending on the operating conditions. In this work, we present a systematic analysis of SEM noise distributions using experimental images acquired under different accelerating voltages and dwell times with the in-lens and in-chamber secondary electron (SE) detectors, as well as the back-scattered electron (BSE) detector. Statistical tests, histogram analysis, and distribution fitting were employed to identify the underlying noise distributions. The results show that, at short dwell times, SE noise is best described by a Neyman Type-A distribution, whereas BSE noise is better described by a Gamma distribution. To automate the classification of these noise distributions, a deep learning framework based on convolutional neural networks (CNN) with a Convolutional Block Attention Module (CBAM) was implemented. Pretrained architectures were evaluated and compared with the proposed model. Among the pretrained models, MobileNetV2 achieved the highest accuracy of 88%, whereas the proposed CNN-CBAM model achieved the best overall performance, with F1-scores up to 0.98 and an accuracy of 97%.

Schlagwörter

Stichwörter der Autor:innen

Deep learningNoise distribution classificationSEM noiseScanning electron microscopy

Autor:innen und Institutionen

  • Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology, 54 Lomb Memorial Drive, Rochester, 14623, NY, United States. Electronic address: mm5111@rit.edu.
  • Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology, 54 Lomb Memorial Drive, Rochester, 14623, NY, United States. Electronic address: surya.kamal@rit.edu.
  • Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology, 54 Lomb Memorial Drive, Rochester, 14623, NY, United States.

Zitieren

APA

Nyaburi, K. M., Kamal, S., & Hailstone, R. K. (2027). Scanning electron microscopy noise classification using deep learning. Micron, 209, 104137. https://doi.org/10.1016/j.micron.2026.104137

Vancouver

Nyaburi KM, Kamal S, Hailstone RK. Scanning electron microscopy noise classification using deep learning. Micron. 2027;209:104137. doi:10.1016/j.micron.2026.104137

BibTeX
@article{Nyaburi2027,
  author = {Nyaburi, Kevin Mogere and Kamal, Surya and Hailstone, Richard K},
  title = {Scanning electron microscopy noise classification using deep learning},
  journal = {Micron},
  year = {2027},
  volume = {209},
  pages = {104137},
  doi = {10.1016/j.micron.2026.104137}
}
Kostenlos starten →