Year: 2022
Type: conference-paper
Abstract: The oracle bone script is the oldest writing system in China, and as the origin of Chinese characters, it is also the earliest cultural heritage in China. With the development of computer technology, deep learning has become an important technology of image classification and played a very significant role in oracle research. In this paper, oracle bone inscription recognition is proposed based on semi-supervised self-training learning, which learns the relationship between oracle bones, clementi, seal script and official script, and uses other existing font features to learn oracle bone characters. In the experiment, the detection accuracy of oracle script fonts has reached 87.9%, and the probability of character recognition is 28.2%, which proves that there is a certain relationship in the development of oracle bone inscriptions.
Authors: Junya Liu, Rujia Li, Ting Fu, Zhijian Yin, Zhen Yang
Institution: Jiangxi Science and Technology Normal University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4362564518