| Peer-Reviewed

Damage Detection of Guqin in CT Images Based on Deep Neural Network

Received: 25 August 2022     Accepted: 7 September 2022     Published: 27 September 2022
Views:       Downloads:
Abstract

Guqin is the treasure of Chinese heritage culture and the top listed musical instrument. Among the Guqin collected in the Palace Museum, the most famous Guqin named Jiuxiao Huanpei was made by Lei Wei in the Tang Dynasty, which was regarded as an invaluable treasure and ranked first in the Palace Museum. There is a very rare situation in its internal structure where in the Dragon Pool, we saw a round ditch with a width of 2 cm and a depth of 1 cm, there is no such groove in the belly of an ordinary Guqin. This structure has led many well-known modern musical instrument makers to deliberately design their Guqin like this, because they believe that this is the exquisite design of the ancient master, which can make the sound performance better. Few people have questioned it for hundreds of years. Nowadays, the artificial intelligence technology in the world is developing very fast, among which the model used for object detection has gradually improved its accuracy. This paper applies the YOLO model in deep learning to train with 7803 CT slices of Guqin, and then tests the Jiuxiao Huanpei Guqin in the Forbidden City and several other Guqins. The conclusion is that this Guqin was not intended to be designed to that model, it was likely damaged, and like the Emperor’s New Clothes, no one except AI can tell the truth. The purpose of this paper is to arouse people's attention to the establishment of digital scientific analysis for cultural heritage.

Published in American Journal of Computer Science and Technology (Volume 5, Issue 3)
DOI 10.11648/j.ajcst.20220503.15
Page(s) 184-189
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2022. Published by Science Publishing Group

Keywords

Guqin, CT, 3D, Deep Neural Network, YOLO

References
[1] baike. 2022, Baidu Baike. Retrieved 5 September 2022 from https://baike.baidu.com/item/%E9%9B%B7%E5%A8%81/4895588?fr=aladdin
[2] Minzhong Zheng, Guqin in the collection of the palace museum, Classics of the forbidden city, Compiled by the palace museum, the forbidden city publishing house, ISBN 978-7-5134-0011-4, 2010.7 (2014. 3 Reprint), CIP (2010) No. 134529.
[3] Zhao Xihu, Dongtian Qinglu, Southern Song Dynasty (1225-1264).
[4] China Archives, March 20, 2020, No. 3501, 4th Edition.
[5] “A Documentary about the production of ancient Guqin”, Xihe Guqin Manufactory Studio.
[6] Yang J, Li S B, Gao Z, Wang Z, Liu W. Real-time recognition method for 0.8 cm darning needles and KR22 bearings based on convolution neural networks and data increase. Applied Sciences, 2018, 8 (10): Article No. 1857.
[7] Yang G C, Yang J, Sheng W H, Junior F E F, Li SB. Convolutional neural network-based embarrassing situation detection under camera for social robot in smart homes. Sensors, 2018, 18 (5): Article No. 1530.
[8] Zhang Hui, Wang Kun-Feng, Wang Fei-Yue. Advances and perspectives on applications of deep learning in visual object detection. Acta Automatica Sinica, 2017, 43 (8): 1289−1305.
[9] Fang F, Li L, Gu Y, et al. A novel hybrid approach for crack detection. Pattern Recognition, 2020, 107: 107474.
[10] Yang J, Yang G C. Modified convolutional neural network based on dropout and the stochastic gradient descent optimizer. Algorithms, 2018, 11 (3): Article No. 28.
[11] Bergmann P, L¨owe S, Fauser M, Sattlegger D, Steger C. Improving unsupervised defect segmentation by applying structural similarity to autoencoders. arXiv preprint arXiv: 1807.02011, 2018.
[12] Tao X, Wang Z H, Zhang Z T, Zhang D P, Xu D, Gong XY, et al. Wire defect recognition of spring-wire socket using multitask convolutional neural networks. IEEE Transactions on Components, Packaging and Manufacturing Technology, 2018, 8 (4): 689−698.
[13] Xue Y D, Li Y C. A fast detection method via regionbased fully convolutional neural networks for shield tunnellining defects. Computer-Aided Civil and Infrastructure Engineering, 2018, 33 (8): 638−654.
[14] Lei J, Gao X, Feng Z L, Qiu H M, Song M L. Scale in sensitive and focus driven mobile screen defect detection in industry. Neurocomputing, 2018, 294: 72−81.
[15] Asya Toskova, Zlatina Uhr, Stanimir Stoyanov, Borislav Toskov, DCNN against Wheat Weeds, Bulgarian Academy of Sciences, December 2020, Vol. 74, pp. 41-50, DOI: 10.7546/PECR.74.20.05.
[16] Derya Soydaner, Rolling in the Deep Convolutional Neural Networks, December 2019, International Journal of Intelligent Systems and Applications in Engineering.
[17] Alex Pentland, Extraction of Deformable Part Models. January 1990, Computer Vision - ECCV'90, First European Conference on Computer Vision, Antibes, France, April 23-27, 1990, Proceedings, DOI: 10.1007/BFb0014888.
[18] Zhengxia Zou, Zhenwei Shi, Member, IEEE, Yuhong Guo, and Jieping Ye, Senior Member, Object Detection in 20 Years: A Survey, IEEE, May 2019, doi.org/10.48550/arXiv.1905.05055.
[19] Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi, You Only Look Once: Unified, Real-Time Object Detection, Computer Vision and Pattern Recognition, Jun 2015. https://doi.org/10.48550/arXiv.1506.02640
[20] Joseph Redmon, Ali Farhadi, YOLOv3: An Incremental Improvement, Computer Vision and Pattern Recognition, April 2018, doi.org/10.48550/arXiv.1804.02767.
[21] Chao Peng, Tete Xiao, Zeming Li, Yuning Jiang, Xiangyu Zhang, Kai Jia Gang Yu, Jian Sun, MegDet A Large Mini-Batch Object Detector, Computer Vision Foundation, IEEE Xplore.
[22] Michael Pyrkosz, Charles Van Karsen, George Bissinger, “Converting CT Scans of a Stradivari Violin to a FEM”, IMAC-XXVIII, 2010, Jacksonville, Florida USA.
Cite This Article
  • APA Style

    Yingxi Tang. (2022). Damage Detection of Guqin in CT Images Based on Deep Neural Network. American Journal of Computer Science and Technology, 5(3), 184-189. https://doi.org/10.11648/j.ajcst.20220503.15

    Copy | Download

    ACS Style

    Yingxi Tang. Damage Detection of Guqin in CT Images Based on Deep Neural Network. Am. J. Comput. Sci. Technol. 2022, 5(3), 184-189. doi: 10.11648/j.ajcst.20220503.15

    Copy | Download

    AMA Style

    Yingxi Tang. Damage Detection of Guqin in CT Images Based on Deep Neural Network. Am J Comput Sci Technol. 2022;5(3):184-189. doi: 10.11648/j.ajcst.20220503.15

    Copy | Download

  • @article{10.11648/j.ajcst.20220503.15,
      author = {Yingxi Tang},
      title = {Damage Detection of Guqin in CT Images Based on Deep Neural Network},
      journal = {American Journal of Computer Science and Technology},
      volume = {5},
      number = {3},
      pages = {184-189},
      doi = {10.11648/j.ajcst.20220503.15},
      url = {https://doi.org/10.11648/j.ajcst.20220503.15},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajcst.20220503.15},
      abstract = {Guqin is the treasure of Chinese heritage culture and the top listed musical instrument. Among the Guqin collected in the Palace Museum, the most famous Guqin named Jiuxiao Huanpei was made by Lei Wei in the Tang Dynasty, which was regarded as an invaluable treasure and ranked first in the Palace Museum. There is a very rare situation in its internal structure where in the Dragon Pool, we saw a round ditch with a width of 2 cm and a depth of 1 cm, there is no such groove in the belly of an ordinary Guqin. This structure has led many well-known modern musical instrument makers to deliberately design their Guqin like this, because they believe that this is the exquisite design of the ancient master, which can make the sound performance better. Few people have questioned it for hundreds of years. Nowadays, the artificial intelligence technology in the world is developing very fast, among which the model used for object detection has gradually improved its accuracy. This paper applies the YOLO model in deep learning to train with 7803 CT slices of Guqin, and then tests the Jiuxiao Huanpei Guqin in the Forbidden City and several other Guqins. The conclusion is that this Guqin was not intended to be designed to that model, it was likely damaged, and like the Emperor’s New Clothes, no one except AI can tell the truth. The purpose of this paper is to arouse people's attention to the establishment of digital scientific analysis for cultural heritage.},
     year = {2022}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Damage Detection of Guqin in CT Images Based on Deep Neural Network
    AU  - Yingxi Tang
    Y1  - 2022/09/27
    PY  - 2022
    N1  - https://doi.org/10.11648/j.ajcst.20220503.15
    DO  - 10.11648/j.ajcst.20220503.15
    T2  - American Journal of Computer Science and Technology
    JF  - American Journal of Computer Science and Technology
    JO  - American Journal of Computer Science and Technology
    SP  - 184
    EP  - 189
    PB  - Science Publishing Group
    SN  - 2640-012X
    UR  - https://doi.org/10.11648/j.ajcst.20220503.15
    AB  - Guqin is the treasure of Chinese heritage culture and the top listed musical instrument. Among the Guqin collected in the Palace Museum, the most famous Guqin named Jiuxiao Huanpei was made by Lei Wei in the Tang Dynasty, which was regarded as an invaluable treasure and ranked first in the Palace Museum. There is a very rare situation in its internal structure where in the Dragon Pool, we saw a round ditch with a width of 2 cm and a depth of 1 cm, there is no such groove in the belly of an ordinary Guqin. This structure has led many well-known modern musical instrument makers to deliberately design their Guqin like this, because they believe that this is the exquisite design of the ancient master, which can make the sound performance better. Few people have questioned it for hundreds of years. Nowadays, the artificial intelligence technology in the world is developing very fast, among which the model used for object detection has gradually improved its accuracy. This paper applies the YOLO model in deep learning to train with 7803 CT slices of Guqin, and then tests the Jiuxiao Huanpei Guqin in the Forbidden City and several other Guqins. The conclusion is that this Guqin was not intended to be designed to that model, it was likely damaged, and like the Emperor’s New Clothes, no one except AI can tell the truth. The purpose of this paper is to arouse people's attention to the establishment of digital scientific analysis for cultural heritage.
    VL  - 5
    IS  - 3
    ER  - 

    Copy | Download

Author Information
  • National Remote Sensing Lab., Zhicheng International Academy, Beijing, China

  • Sections