EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Research on the semantic segmentation of Thangka images via an improved PIDNet

Jiao Wu, Tiejun Wang iD, Xiaoyan Hu, LingMei Tao, Tianjiao Duan, Yanjiao Wei

PLOS One · 14.05.2026 · 21 (5) · e0332164

DOI: 10.1371/journal.pone.0332164 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 14.05.2026. Verfasst von Jiao Wu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Language and Cultural Computing of the Ministry of Education Northwest Minzu University, Lanzhou, Gansu, China. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Semantics. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities, Natural Science Foundation of Gansu Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the digital preservation, restoration, and research of Thangka paintings, real-time semantic segmentation plays a crucial role in rapid image analysis. However, Thangka images exhibit intricate compositions, where principal figures often blend with backgrounds, ritual objects, and intricate ornaments, leading to blurred boundaries and fine details that challenge conventional segmentation methods in balancing accuracy and efficiency. To address this, we propose an improved PIDNet-based model incorporating ECA-Pag (Efficient Channel Attention-Path Aggregation) and LGFM (Local-Global Feature Fusion Module) modules, along with PConv3 (Partial Convolution 3), enhancing feature extraction and segmentation precision. Experimental results demonstrate that our model achieves 73.28% mIoU and mB-Fscore (mean Boundary F-score) of 40.01% on a custom Thangka dataset while maintaining 109.03 FPS (Frames Per Second), ensuring both high accuracy and real-time performance. Furthermore, evaluations on the Cityscapes benchmark confirm the model’s generalization capability, outperforming baseline methods. This work provides an efficient and reliable solution for Thangka image segmentation, with potential applications in cultural heritage preservation and broader computer vision tasks.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedSemanticsAlgorithmsConvolutional Neural NetworksHumans

Autor:innen und Institutionen

  • Key Laboratory of Language and Cultural Computing of the Ministry of Education Northwest Minzu University, Lanzhou, Gansu, China.
  • School of Mathematics and Computer Science Northwest Minzu University, Lanzhou, Gansu, China.
  • Gansu Provincial Engineering Research Center for Multimodal Artificial Intelligence, Lanzhou, Gansu, China.

ORCID-Profile: Tiejun Wang

Förderung

  • National Natural Science Foundation of China
  • Fundamental Research Funds for the Central Universities
  • Natural Science Foundation of Gansu Province

Zitieren

APA

Wu, J., Wang, T., Hu, X., Tao, L., Duan, T., & Wei, Y. (2026). Research on the semantic segmentation of Thangka images via an improved PIDNet. PLOS One, 21(5), e0332164. https://doi.org/10.1371/journal.pone.0332164

Vancouver

Wu J, Wang T, Hu X, Tao L, Duan T, Wei Y. Research on the semantic segmentation of Thangka images via an improved PIDNet. PLOS One. 2026;21(5):e0332164. doi:10.1371/journal.pone.0332164

BibTeX
@article{Wu2026,
  author = {Wu, Jiao and Wang, Tiejun and Hu, Xiaoyan and Tao, LingMei and Duan, Tianjiao and Wei, Yanjiao},
  title = {Research on the semantic segmentation of Thangka images via an improved PIDNet},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {5},
  pages = {e0332164},
  doi = {10.1371/journal.pone.0332164}
}
Kostenlos starten →