Identification of Ancient Ceramic by Convolution Neural Network
SUN He-yang1, ZHOU Yue1, 2, LI Si-jia1, 2, LI Li1, YAN Ling-tong1, FENG Xiang-qian1*
1. Institute of High Energy Physics, Chinese Academy of Sciences, Beijing 100049, China
2. University of Chinese Academy of Sciences, Beijing 100049, China
Abstract：As a treasure of Chinese culture, ancient ceramics have been sought at home and abroad since ancient times. With the development of ancient commerce and trade, ancient Chinese ceramics spread worldwide and were collected by private individuals or museums. Some were collected in museums after being excavated from tombs and salvaged from sunken ships. Tracing the origin of such ancient ceramics has always been the focus of ceramic archaeology, which is of great significance to studying ancient commerce and cultural exchanges. Using a portable digital microscope, spectrophotometer, X-ray fluorescence and other methods, the celadon porcelain samples excavated from Housi'ao, Silongkou, Fengdongyan and Yaozhou kilns were analyzed, and the data of the microbubble size distribution characteristics, ultraviolet, visible near-infrared spectrum characteristics and glaze composition of the celadon porcelain samples from these four kilns were obtained. The convolution neural network classification model was established by using these three features as variables for training and verification. The results show that the microbubble size distribution features, ultraviolet, visible near-infrared spectral features and glaze composition data of celadon porcelain are effective, but the difference in classification accuracy is very obvious.The average accuracy of model training of 30 randomly divided training sets and test sets: the model of microbubble size distribution features is 75%, the model of ultraviolet, visible near-infrared spectrum features is 89.2%, and the model of component data is 92.1%.The accuracy of the glaze composition data model is the highest, and the difference between the accuracy of training sets and test sets is the smallest. After saving the model parameters trained based on different features for fusion and retraining, it was found that the accuracy of the model after the fusion of ultraviolet, visible and near-infrared spectral features and microbubble size distribution features was improved to 93.7% and the accuracy of the model after the fusion of the three features was improved to the highest 97.4%. The results of the five-fold cross-validation show that the model, after the fusion of multiple features, can effectively avoid the case that the single feature model has many cross misjudgments on the samples from Housi'ao and Silongkou. In general, it is feasible to explore more effective classification features of ancient ceramics based on convolutional neural networks to trace the source of ancient ceramics accurately.
Key words：Convolutional neural network;Bubble; UV-visible near infrared spectroscopy; X-ray fluorescence;Celadon
孙合杨，周 越，黎思佳，李 丽，闫灵通，冯向前. 基于卷积神经网络的古陶瓷窑口甄别[J]. 光谱学与光谱分析, 2024, 44(02): 354-358.
SUN He-yang, ZHOU Yue, LI Si-jia, LI Li, YAN Ling-tong, FENG Xiang-qian. Identification of Ancient Ceramic by Convolution Neural Network. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(02): 354-358.
[1] Wood N，Li He. Archaeometry, 2015, 57(4): 617.
[2] Li Yuanqiu, Yang Yimin, Zhu Jian, et al. Ceramics International, 2016, 42(7): 8495.
[3] Shi Pei, Wang Fen, Wang Yi, et al. Ceramics International, 2017, 43(15): 11616.
[4] Wen Rui, Wang Dong, Wang Lihua, et al. Ceramics International, 2019, 45(8): 10589.
[5] Li Weidong, Luo Hongjie, Li Jianan, et al. Ceramics International, 2011, 37(2): 651.
[6] Jiang Xiaochenyang, Weng Yanjun, Wu Xiaohong, et al. Proceedings of the National Academy of Sciences, 2020, 117(12): 6446.
[7] Li Weidong, Li Jiazhi, Wu Jun, et al. Ceramics International, 2003, 29(8): 933.
[8] Wu Juan, Zhang Maolin, Hou Tiejun, et al. Ceramics International, 2015, 41(5): 6851.
[9] Li L, Feng S L, Feng X Q, et al. Nuclear Instruments & Methods in Physics Research Section B-Beam Interactions with Materials and Atoms, 2012, 292: 25.
[10] Huang Jizhong，Guan Yepeng. Sensors, 2021, 21(4): 1318.
[11] Sun Shiliang, Cao Zehui, Zhu Han, et al. IEEE Transactions on Cybernetics, 2020, 50(8): 3668.
