Content area

Abstract

Translate

Chinese ancient inscriptions have a long history, while natural erosion and human destruction have led to many incomplete inscriptions with low-quality textual data and blurry images. With deep learning technologies, it is expected to use relevant image and language processing tasks to restore inscriptions. To improve the efficiency of restoration tasks and promote the digital protection of cultural heritage, this study used deep learning technology to restore ancient Chinese inscriptions. We combined natural language processing and computer vision technologies to train models for restoring inscriptions. The results indicated that the joint solution had advantages over every single model for incomplete character restoration.

Details

1009240
Subject
Calligraphy;
Machine learning;
Accuracy;
Deep learning;
Artificial intelligence;
Books;
Neural networks;
Image restoration;
Computer vision;
Natural language processing;
Image quality;
Inscriptions;
Cultural resources;
Cultural heritage
Business indexing term
Identifier / keyword
Information and Computing Sciences; Artificial Intelligence and Image Processing
Title
Chinese inscription restoration based on artificial intelligent models
Author
Wang, Zhen 1 ; Li, Yujun 2 ; Li, Honglei 1 

1  Liaoning Normal University, Digital Protection and Utilisation Laboratory of Historical and Cultural Heritage, Dalian, China (GRID:grid.440818.1) (ISNI:0000 0000 8664 1765) 
2  Liaoning Normal University, School of History and Culture, Dalian, China (GRID:grid.440818.1) (ISNI:0000 0000 8664 1765) 
Publication title
Heritage Science; London
Volume
13
Issue
1
Pages
326
Publication year
2025
Publication date
Dec 2025
Publisher
Springer Nature B.V.
Place of publication
London
Country of publication
Netherlands
Publication subject
Archaeology, Chemistry
e-ISSN
20507445
Source type
Scholarly Journal
Language of publication
English
Document type
Journal Article
Publication history
 
 
Online publication date
2025-07-05
Milestone dates
2025-06-20 (Registration); 2025-05-20 (Received); 2025-06-20 (Accepted)
Publication history
 
 
   First posting date
05 Jul 2025
DOI
https://doi.org/10.1038/s40494-025-01900-x
ProQuest document ID
3227339378
Document URL
https://www.proquest.com/scholarly-journals/chinese-inscription-restoration-based-on/docview/3227339378/se-2?accountid=208611
Copyright
© The Author(s) 2025. This work is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Last updated
2025-10-16
Database
ProQuest One Academic