Advertisement

Ancient Asian Character Recognition for Literature Preservation and Understanding

  • Lin Meng
  • C. V. Aravinda
  • K. R. Uday Kumar Reddy
  • Tomonori Izumi
  • Katsuhiro Yamazaki
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11196)

Abstract

This paper introduces a project for automatically recognizing ancient Asian characters by image processing and deep learning with the aim of preserving Asian culture. The ancient characters examined include Chinese and Indian characters, which are the most mysterious, wildly used, and historic in the ancient world, and also feature multiply types. The automatic recognition method consists of preprocessing and recognition processing. The preprocessing includes character segmentation and noise reduction, and the recognition processing has a conventional recognition and deep learning. The conventional recognition method consists of feature extraction and similarity calculation or classification, and data augmentation is a key part of the deep learning. Experimental results show that deep learning achieves a better recognition accuracy than conventional image processing. Our aim is to preserve ancient literature by digitizing it and clarifying the characters and how they change throughout history by means of accurate character recognition. We also hope to help people discover new knowledge from ancient literature.

Keywords

Ancient Asian character recognition Character segmentation Noise reduction Deep learning Ancient literature preservation Ancient literature discovery 

References

  1. 1.
    Pu, M.Z., Xie, H.Y.: Shanghai Bo Wu Guan Cang Jia Gu Wen Zi. Shanghai Bo Wu Guan (2009)Google Scholar
  2. 2.
    Rubbing characters Database (Kyoto University). http://coe21.zinbun.kyoto-u.ac.jp/djvuchar. Accessed 8 Aug 2018
  3. 3.
    Meng, L., Fujikawa, Y., Ochiai, A., Izumi, T., Yamazaki, K.: Recognition of oracular bone inscriptions using template matching. Int. J. Comput. Theory Eng. 8(1), 53–57 (2016). (in Japanese)CrossRefGoogle Scholar
  4. 4.
    Meng, L., Izumi, T., Oyanagi, S.: Recognition of oracular bone inscriptions by clustering and matching on the hough space. J. Inst. Image Electron. Eng. Jpn. 44(4), 627–636 (2015). (in Japanese)Google Scholar
  5. 5.
    Meng, L.: Recognition of oracle bone inscriptions by extracting line features on image processing. In: Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2017), pp. 606–611 (2017)Google Scholar
  6. 6.
    Meng, L.: Two-stage recognition for oracle bone inscriptions. In: Battiato, S., Gallo, G., Schettini, R., Stanco, F. (eds.) ICIAP 2017. LNCS, vol. 10485, pp. 672–682. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-68548-9_61CrossRefGoogle Scholar
  7. 7.
    Meng, L.: Recognition of Oracle Bone Inscriptions Using Image Processing, 1st edn. HOKUTO PRINT, Kyoto (2016). (in Japanese)Google Scholar
  8. 8.
    Ochiai, A.: Oracle Bone Inscriptions Database. http://koukotsu.sakura.ne.jp/top.html. Accessed 8 Aug 2018
  9. 9.
    Kamitoku, N., Meng, L., Yamazaki, K.: Recognition of oracle bone inscriptions using deep learning. In: The 80th National Convention of Information Processing Society of Japan, 2S-07 (2018). (in Japanese)Google Scholar
  10. 10.
    Watanabe, S., Meng, L., Izumi, T.: Methods to extract character regions of oracle bone inscriptions. In: The 248th Technical Report of the Institute of Image Electronics Engineers of Japan (2018). (in Japanese)Google Scholar
  11. 11.
    Kishi, M., Nabeya, M., Nogami, K., Meng, L., Yamazaki, K.: Multi-typeface recognition of rubbing using deep learning and creation of spatiotemporal database. In: The 80th National Convention of Information Processing Society of Japan, 2S-08 (2018). (in Japanese)Google Scholar
  12. 12.
    Aravinda, C.V., Prakash, H.N.: A review on various HandWritten cursive characters segmentation techniques. In: 2nd International Conference on Applied and Theoretical Computing and Communication Technology (iCATccT), pp. 647–651 (2016)Google Scholar
  13. 13.
    Aravinda, C.V., Prakash, H.N.: A review recognition for south india languages using statistical feature extraction and distance classifier. Int. J. Nat. Lang. Comput. (IJNLC) 5(4), 37–48 (2016)CrossRefGoogle Scholar
  14. 14.
    Aravinda, C.V., Prakash, H.N.: Template matching method for Kannada Handwriten recognition based on correlation analysis. In: 2014 International Conference on Contemporary Computing and Informatics (IC3I), pp. 857–861 (2014)Google Scholar
  15. 15.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems 25 (NIPS 2012) (2012)Google Scholar
  16. 16.
    Szegedy, C., et al.: Going deeper with convolutions. In : 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015) (2015)Google Scholar
  17. 17.
    Aravinda, C.V., Prakash, H.N.: A machine editable format for Kannada handwritten character recognition using a dissect and connect technique. IJETAE 4, 1–5 (2014)CrossRefGoogle Scholar
  18. 18.
    Aravinda, C.V., Prakash, H.N., Lavanya, S.: Kannada handwritten character recognition using multi feature extraction technique. Int. J. Sci. Res. (IJSR) 3(10), 911–916 (2014)Google Scholar
  19. 19.
    Aravinda, C.V., Prakash, H.N.: Template matching method for kannada handwritten recognition based on correlation analysis. In: 2014 International Conference on Contemporary Computing and Informatics (IC3I) (2014)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Department of Electronic and Computer EngineeringRitsumeikan UniversityKusatsuJapan
  2. 2.Department of Computer Science and EngineeringN.M.A.M. Institute of TechnologyKarkalaIndia

Personalised recommendations