EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Ancient Chinese Character Recognition with Improved Swin-Transformer and Flexible Data Enhancement Strategies

Yi Zheng, Yi Chen iD, Xianbo Wang iD, Donglian Qi, Yunfeng Yan

Sensors · 28.03.2024 · 24 (7) · 2182

DOI: 10.3390/s24072182 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 28.03.2024. Verfasst von Yi Zheng und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Key R&D Project of Zhejiang Province, Sanya Science and Technology Innovation Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The decipherment of ancient Chinese scripts, such as oracle bone and bronze inscriptions, holds immense significance for understanding ancient Chinese history, culture, and civilization. Despite substantial progress in recognizing oracle bone script, research on the overall recognition of ancient Chinese characters remains somewhat lacking. To tackle this issue, we pioneered the construction of a large-scale image dataset comprising 9233 distinct ancient Chinese characters sourced from images obtained through archaeological excavations. We propose the first model for recognizing the common ancient Chinese characters. This model consists of four stages with Linear Embedding and Swin-Transformer blocks, each supplemented by a CoT Block to enhance local feature extraction. We also advocate for an enhancement strategy, which involves two steps: firstly, conducting adaptive data enhancement on the original data, and secondly, randomly resampling the data. The experimental results, with a top-one accuracy of 87.25% and a top-five accuracy of 95.81%, demonstrate that our proposed method achieves remarkable performance. Furthermore, through the visualizing of model attention, it can be observed that the proposed model, trained on a large number of images, is able to capture the morphological characteristics of ancient Chinese characters to a certain extent.

Schlagwörter

Stichwörter der Autor:innen

Swin-Transformerancient Chinese characterscharacter recognitioncultural heritage

Autor:innen und Institutionen

  • College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China.
  • Hainan Institute of Zhejiang University, Sanya 572025, China.
  • School of Mechanical Engineering, Zhejiang University, Hangzhou 310027, China.

ORCID-Profile: Yi Chen, Xianbo Wang

Förderung

  • National Natural Science Foundation of China
  • Key R&D Project of Zhejiang Province
  • Sanya Science and Technology Innovation Project
  • Research Startup Funding from Hainan Institute of Zhejiang University
  • The National Social Science Fund of China
  • Key R&D Project of Zhejiang Province
  • Research Startup Funding from the Hainan Institute of Zhejiang University

Zitieren

APA

Zheng, Y., Chen, Y., Wang, X., Qi, D., & Yan, Y. (2024). Ancient Chinese Character Recognition with Improved Swin-Transformer and Flexible Data Enhancement Strategies. Sensors, 24(7), 2182. https://doi.org/10.3390/s24072182

Vancouver

Zheng Y, Chen Y, Wang X, Qi D, Yan Y. Ancient Chinese Character Recognition with Improved Swin-Transformer and Flexible Data Enhancement Strategies. Sensors. 2024;24(7):2182. doi:10.3390/s24072182

BibTeX
@article{Zheng2024,
  author = {Zheng, Yi and Chen, Yi and Wang, Xianbo and Qi, Donglian and Yan, Yunfeng},
  title = {Ancient Chinese Character Recognition with Improved Swin-Transformer and Flexible Data Enhancement Strategies},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {7},
  pages = {2182},
  doi = {10.3390/s24072182}
}
Kostenlos starten →