EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

EISC: Enforcing Consistency Across Different Scales for Metallographic Image Segmentation

Honggang Li, Yiming Zhang, Shiyu Du

Electronics · 03.08.2026 · 15 (15) · 3425

DOI: 10.3390/electronics15153425 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 03.08.2026. Verfasst von Honggang Li und 2 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Advanced Materials National Science and Technology Major Project, Natural Science Foundation of Shanghai Science and Technology Commission, Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Metallographic image segmentation underpins automated metallographic analysis, yet pixel-level annotation is costly. Metallographic microstructures exhibit dramatic size differences, including cross-scale structures such as large-scale matrix phases, grain boundary cementite networks, and acicular Widmanstätten structures. Existing feature extraction modules cannot balance the semantic integrity of large regions and the fine details of microstructures, causing missed small microstructures and blurred segmentation boundaries. Current semi-supervised methods only impose consistency constraints on perturbed input images at the final prediction output, ignoring multi-scale semantic features from decoder upsampling stages. This leads to noisy supervision signals, low-quality pseudo-labels, and poor generalization. To address these issues, this paper proposes a semi-supervised metallographic image segmentation model, EISC, integrating MT cross-network scale feature extraction and decoder multi-scale consistency constraints. It adaptively fuses multi-receptive-field features and introduces a regularization term to maintain the semantic consistency of multi-scale decoder outputs, improving pseudo-label quality. Comparative and ablation experiments verify that EISC effectively enhances the segmentation accuracy and robustness of metallographic images.

Förderung

  • the Advanced Materials National Science and Technology Major Project
  • Natural Science Foundation of Shanghai Science and Technology Commission
  • Fundamental Research Funds for the Central Universities
  • the Peak Disciplines (Type IV) of Institutions of Higher Learning in Shanghai, the Ningbo Natural Science Foundation
  • the National Key R&D Program of China
  • National Natural Science Foundation of China
  • the Key R&D Projects of Zhejiang Province
  • the National Key Laboratory of Nuclear Reactor Technology

Zitieren

APA

Li, H., Zhang, Y., & Du, S. (2026). EISC: Enforcing Consistency Across Different Scales for Metallographic Image Segmentation. Electronics, 15(15), 3425. https://doi.org/10.3390/electronics15153425

Vancouver

Li H, Zhang Y, Du S. EISC: Enforcing Consistency Across Different Scales for Metallographic Image Segmentation. Electronics. 2026;15(15):3425. doi:10.3390/electronics15153425

BibTeX
@article{Li2026,
  author = {Li, Honggang and Zhang, Yiming and Du, Shiyu},
  title = {EISC: Enforcing Consistency Across Different Scales for Metallographic Image Segmentation},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {15},
  pages = {3425},
  doi = {10.3390/electronics15153425}
}
Kostenlos starten →