Abstract—In this paper, we describe a new deep learning model for Oracle Bone Inscriptions recognition (OBIs). OBIs are early hieroglyphs in China, which to realize the rapid and accurate image retrieval of large scale oracle bones datasets and break through the limitations of current conventional retrieval methods. With the collected images of the oracle-like characters as input, the model extracts the image features by itself and implicitly learns from the training data to automatically recognize the oracle-like characters. Experimental results show that the proposed method can achieve a high recognition rate. In particular, the accuracy rate of the first 5 prediction categories (top-5) reaches 94.2%, which significantly decreases the search speculation space of archaeological researchers and improves the efficiency and accuracy of OBIs recognition.
Index Terms—convolutional neural network, oracle bone inscriptions, recognition
Cite: Mengting Liu, Guoying Liu, Yongge Liu, and Qingju Jiao, "Oracle Bone Inscriptions Recognition Based on Deep Convolutional Neural Network," Journal of Image and Graphics, Vol. 8, No. 4, pp. 114-119, September 2020. doi: 10.18178/joig.8.4.114-119
Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.
Copyright © 2012-2020 Journal of Image and Graphics, All Rights Reserved