Application of Neural Network in Oracle Bone Inscriptions

Mengting Liu, Feng Gao, Bang Li, Guoying Liu

Abstract: The recognition of Oracle Bone Inscriptions(OBIs) is of great significance to archaeology, history, and linguistics. To realize the fast and accurate retrieval of images for large-scale OBIs datasets and break through the limitations of current conventional retrieval methods, this paper proposes a convolutional neural network for OBIs recognition. The model is designed according to the characteristics of OBIs. The experimental results show that the improved network can better extract the features of OBIs characters, and the recognition rate reaches 84.45%, which is 13.74% higher than the network before the improvement.