Utilization of generative adversarial networks (GANs) in the replication and restoration of calligraphy art
Abstract
With the continuous integration of culture and technology, the replication and restoration of calligraphy art has become a new direction in the restoration of traditional calligraphy and painting. The research on the replication and restoration of calligraphy art is of great significance in contemporary art. However, the accuracy and authenticity of the replicas in the process of replication and restoration calligraphy art are not high, and there are significant differences in material selection. This paper started with GAN (Generative Adversarial Network), collected a large amount of image data from calligraphy art works, trained a generative adversarial network, and used the trained model to process calligraphy art works. Compared with traditional replication techniques, the cost, restoration efficiency, and cultural inheritance and recognition of the two in calligraphy art replication were analyzed. Research has found that the highest score for the restoration of calligraphy art quality using traditional methods can only reach 89.9 points (out of a total of 100 points), while the highest score for GAN can reach 96.4 points. Moreover, the application of GAN can save the cost of calligraphy art for restoration, improve restoration efficiency, and enable flexible application in different scenarios.
References
1. Mostovshchykova D. Calligraphy in enamel art: World and Ukrainian experience[J]. International Journal of Conservation Science, 2022, 13(2): 619-628.
2. Dang R, Kang Y, Tan H. Color Damage of Visible Light on Plain-Woven Silk in Different Conservation States of Paintings and Calligraphy in Collections[J]. Fibers and Polymers, 2024, 25(1): 235-242.
3. Liu K, Wu H, Gao Y. Archaeology and virtual simulation restoration of costumes in the Han Xizai banquet painting[J]. AUTEX Research Journal, 2023, 23(2): 238-252.
4. Zhu Wenjun. Ancient book restoration and painting and calligraphy mounting technology from the perspective of cultural inheritance [J]. Beautify Life, 2022 (05): 180-183.
5. Guo D, Ye L, Yan G. CCD-BSM: composite-curve-dilation brush stroke model for robotic chinese calligraphy[J]. Applied Intelligence, 2023, 53(11): 14269-14283.
6. Guoqing Liu. A brief analysis of the experimental teaching construction of cultural relic restoration in colleges and universities [J]. Educational Science Development, 2022, 4(4): 44-46.
7. Xi Chenchen, He Xin, Meng Yalei. Super-resolution method of natural scene text images based on text semantic guidance [J]. Journal of Air Force Engineering University, 2023, 24(6): 96-103.
8. Su B, Liu X, Gao W. A restoration method using dual generate adversarial networks for Chinese ancient characters[J]. Visual Informatics, 2022, 6(1): 26-34.
9. Cao Y, Ma J, Hao C. Tangut character image generation based on cycle-consistent adversarial networks[J]. Journal of Intelligent & Fuzzy Systems, 2023, 44(4): 6341-6358.
10. Zhang J, Shi J, Li M. Triple discriminators-equipped GAN for Denoising of Chinese calligraphic tablet images[J]. Multimedia Tools and Applications, 2022, 81(29): 42691-42711.
Copyright (c) 2024 Xiaojun Zhu
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright on all articles published in this journal is retained by the author(s), while the author(s) grant the publisher as the original publisher to publish the article.
Articles published in this journal are licensed under a Creative Commons Attribution 4.0 International, which means they can be shared, adapted and distributed provided that the original published version is cited.