Study on the evolution of Chinese characters based on few-shot learning: From oracle bone inscriptions to regular script

Abstract

Oracle bone inscriptions (OBIs) are ancient Chinese scripts originated in the Shang Dynasty of China, and now less than half of the existing OBIs are well deciphered. To date, interpreting OBIs mainly relies on professional historians using the rules of OBIs evolution, and the remaining part of the oracle’s deciphering work is stuck in a bottleneck period. Here, we systematically analyze the evolution process of oracle characters by using the Siamese network in Few-shot learning (FSL). We first establish a dataset containing Chinese characters which have finished a relatively complete evolution, including images in five periods: oracle bone inscriptions, bronze inscriptions, seal inscriptions, official script, and regular script. Then, we compare the performance of three typical algorithms, VGG16, ResNet, and AlexNet respectively, as the backbone feature extraction network of the Siamese network. The results show that the highest F1 value of 83.3% and the highest recognition accuracy of 82.67% are obtained by the combination of VGG16 and Siamese network. Based on the analysis, the typical structural performance of each period is evaluated and we identified that the optimized Siamese network is feasible to study the evolution of the OBIs. Our findings provide a new approach for oracle’s deciphering further.

Recognition and Translation of Ancient South Arabian Musnad Inscriptions

“…According to [11], who employed the Siamese network in few-shot learning (FSL),the local feature extraction of Chinese characters performs better using the VGG16 network as the backbone feature extraction network, achieving a recognition accuracy of 82.67%. Meanwhile, [12] the efficient and accurate scene text (EAST) detection model and the feature extractor VGG16 to extract painting inscriptions by combining the characteristics of Chinese paintings, achieving a high accuracy of 89%.…”

Linguistic Studies of Square Characters and Graphic Symbols in Oracle

“…Despite their differences, square characters are closely related to modern Chinese characters, and the study of Oracle inscriptions has provided important insights into the development of Chinese writing. For example, many of the square characters found in Oracle are believed to be early forms of modern Chinese characters [2], which suggests that Oracle played an important role in the evolution of the written language.…”

Music, Language, and Autism: Neurological Insights for Enhanced Learning

“…It was developed into the script for standardizing writing systems by Qin Shihuan (221 BC). Subsequently, Xiaozhuan's prominence paved the way for the Li script (307-217 BC) and the Kai script (202 BC-618 AD), both of which resembled modern Chinese typography [10] . The timeline is not drawn to scale; rather, it is designed to represent the chronological sequence.…”