Algorithm Using Deep Learning for Recognition of Japanese Historical Characters in Photo Image of Historical Book

  • Liao Sichao
  • Hiroyoshi MiwaEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1035)


In Japan, there are vast amount of classical books written in cursive Japanese that cannot be read by modern people. It is difficult to recognize each cursive Japanese separately, because they are written connected. Furthermore, there are many types of shape of characters. Therefore, an efficient method to convert them into modern characters automatically is required. Some methods recognizing a block of a few characters using deep learning have been studied so far. However, every page in a Japanese historical book is stored by a photo image; therefore, it is desirable to recognize all characters in a photo image at once. In this paper, we propose a method using deep learning to recognize cursive Japanese in a photo image without separating a block of characters manually. Furthermore, we evaluate the performance of the proposed algorithm using photo images of an actual book.



This work was partially supported by the Japan Society for the Promotion of Science through Grants-in-Aid for Scientific Research (B) (17H01742) and JST CREST JPMJCR1402.


  1. 1.
    Shoten, I.: General Catalog of National Books. Iwanami Shoten, Chiyoda (2002)Google Scholar
  2. 2.
    Yamamoto, S., Osawa, T.: Labor saving for reprinting Japanese rare classical books: the development of the new method for OCR technology including Kana and Kanji characters in cursive style. Inf. Manag. 58(11), 819–826 (2016)Google Scholar
  3. 3.
    The Dataset of Kuzushiji (Open Data Center for Humanities).
  4. 4.
    Tarin, C., Mikel, B., Asanobu, K., Alex, L., Kazuaki, Y., David, H.: Deep learning for classical Japanese literature. In: Proceedings of 2018 Workshop on Machine Learning for Creativity and Design (Thirty-second Conference on Neural Information Processing Systems), 3 December 2018Google Scholar
  5. 5.
  6. 6.
    National Institute of Japanese Literature.
  7. 7.
    Shibayama, M., et al.: Research on Higher Accuracy Document Character Recognition Systems (in Japanese). Grants-in-Aid for Scientific Research (B)(1) report on research results, pp. 33–49 (2005)Google Scholar
  8. 8.
    Hayasaka, T., Ohno, W., Kato, Y., Yamamoto, K.: Recognition of Hentaigana by deep learning and trial production of WWW application (in Japanese). In: Proceedings of IPSJ Symposium of Humanities and Computer Symposium, pp. 7–12 (2016)Google Scholar
  9. 9.
    Nguyen, H.T., Ly, N.T., Nguyen, K.C., Nguyen, C.T., Nakagawa, M.: Attempts to recognize anomalously deformed Kana in Japanese historical documents. In: Proceedings of 4th International Workshop on Historical Document Imaging and Processing, pp. 31–36, 10–11 November 2017Google Scholar
  10. 10.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of International Conference on Learning Representations, San Diego, 7–9 May 2015Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Graduate School of Science and TechnologyKwansei Gakuin UniversitySanda-shiJapan

Personalised recommendations