Advertisement

Classification of Calligraphy Style Based on Convolutional Neural Network

  • Fengrui Dai
  • Chenwei Tang
  • Jiancheng LvEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11304)

Abstract

Calligraphy is the cultural treasure of the Chinese nation for five millenniums, which has always been loved by the Chinese people. This paper collects a large number of characters of Chinese calligraphy and builds a Chinese characters calligraphy data set. By establishing three different Convolution Neural Network (CNN) models, the features of calligraphy handwriting are extracted. In addition, we use some techniques to improve the robustness and generalization ability of the CNN model, so that the model can adapt to more classification tasks. The experimental results prove that the proposed method can not only well identify the style of different calligraphers, but also have good performance in the classification of the font format of soft pen calligraphy and hard pen calligraphy.

Keywords

Calligraphy classification Characters set Convolution neural network Robustness and generalization 

Notes

Acknowledgments

This work was supported by the National Science Foundation of China (Grant No. 61625204), partially supported by the State Key Program of National Science Foundation of China (Grant No. 61432012 and 61432014).

References

  1. 1.
    Xu, S., Lau, F.C.M., Cheung, W.K., Pan, Y.: Automatic generation of artistic Chinese calligraphy. IEEE Intell. Syst. 20(3), 32–39 (2005)CrossRefGoogle Scholar
  2. 2.
    Zhang, C.X.: On Chinese calligraphy and hard-pen calligraphy. J. Nanyang Norm. Univ. 10, 018 (2010)Google Scholar
  3. 3.
    Li, M., Lv, J., Li, X., Yin, J.: Computer-generated abstract paintings oriented by the color composition of images. Information 8(2), 68 (2017)CrossRefGoogle Scholar
  4. 4.
    Chang, C.Y., Lin, I.C.: An efficient progressive image transmission scheme for Chinese calligraphy. Int. J. Pattern Recognit. Artif. Intell. 20(7), 1077–1092 (2014)CrossRefGoogle Scholar
  5. 5.
    Wang, F.Y., Lu, R., Zeng, D.: Artificial intelligence in China. IEEE Intell. Syst. 23(6), 24–25 (2007)CrossRefGoogle Scholar
  6. 6.
    Xiao, J.: Automatic generation of large-scale handwriting fonts via style learning. In: SIGGRAPH ASIA 2016 Technical Briefs, Association for Computing Machinery (2016)Google Scholar
  7. 7.
    Phan, Q.H., Fu, H., Chan, A.B.: FlexyFont: learning transferring rules for flexible typeface synthesis. Comput. Graph. Forum 34, 245–256 (2015)CrossRefGoogle Scholar
  8. 8.
    Scott, S., Matwin, S.: Feature engineering for text classification. In: International Conference on ICML, pp. 379–388 (1999)Google Scholar
  9. 9.
    Seide, F., Li, G., Chen, X., Yu, D.: Feature engineering in context-dependent deep neural networks for conversational speech transcription. In: Automatic Speech Recognition and Understanding, pp. 24–29 (2011)Google Scholar
  10. 10.
    Zhang, Y., Pezeshki, M., Brakel, P., Zhang, S., Bengio, C.L.Y., Courville, A.: Towards end-to-end speech recognition with deep convolutional neural networks, pp. 410–414 (2017)Google Scholar
  11. 11.
    Sahiner, B., et al.: Classification of mass and normal breast tissue: a convolution neural network classifier with spatial domain and texture images. IEEE Trans. Med. Imaging 15(5), 598–610 (1996)CrossRefGoogle Scholar
  12. 12.
    Lv, J., Yi, Z.: An improved backpropagation algorithm using absolute error function. In: Wang, J., Liao, X., Yi, Z. (eds.) ISNN 2005. LNCS, vol. 3496, pp. 585–590. Springer, Heidelberg (2005).  https://doi.org/10.1007/11427391_93CrossRefGoogle Scholar
  13. 13.
    Lv, J.C., Yi, Z., Zhou, J.: Subspace Learning of Neural Networks. Chemical Rubber Company Press, Incorporated, Boca Raton (2010)Google Scholar
  14. 14.
    Lv, J.C., Tan, K.K., Yi, Z., Huang, S.: A family of fuzzy learning algorithms for robust principal component analysis neural networks. IEEE Trans. Fuzzy Syst. 18(1), 217–226 (2010)CrossRefGoogle Scholar
  15. 15.
    Mcelhaney, R.M: Algorithms for Graphics and Image Processing, pp. 1116–1117. Computer Science Press, Rockville (1982)CrossRefGoogle Scholar
  16. 16.
    Ukil, A.: Support vector machine. Comput. Sci. 1(4), 1–28 (2002)Google Scholar
  17. 17.
    Myronenko, A., Song, X.: Point set registration: coherent point drift. IEEE Trans. Pattern Anal. Mach. Intell. 32(12), 2262–2275 (2010)CrossRefGoogle Scholar
  18. 18.
    Min, W., Baoying, Z., Chenhong, Y., et al.: Chinese calligraphy feature extraction and recognition. Inf. Commun. 7, 19–20 (2015)Google Scholar
  19. 19.
    Wang, J., Lin, F., Chen, J.: Recognition method based on handwritten Chinese characters stroke extraction extraction recombined. Comput. Eng. 33(10), 230–232 (2007)Google Scholar
  20. 20.
    Guo, C., Hu, X.: Feature extraction for calligraphy stroke based on computer image processing. J. Tianjin Univ. Sci. Technol. 25(5), 68–72 (2010)Google Scholar
  21. 21.
    Wen, P.Z., Yao, H., Shen, J.W.: Recognition method of stone inscription font based on convolution neural network. In: Computer Engineering & Design (2018)Google Scholar
  22. 22.
    Yu, W., Yang, K., Bai, Y., Yao, H., Rui, Y.: Visualizing and comparing convolutional neural networks. In: Computer Science (2014)Google Scholar
  23. 23.
    Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Li, F.F.: ImageNet: a large-scale hierarchical image database. In: Computer Vision and Pattern Recognition, pp. 248–255 (2009)Google Scholar
  24. 24.
    Havard, W., Besacier, L., Rosec, O.: SPEECH-COCO: 600k visually grounded spoken captions aligned to MSCOCO data set, pp. 42–46 (2017)Google Scholar
  25. 25.
    Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)MathSciNetzbMATHGoogle Scholar
  26. 26.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift, pp. 448–456 (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Machine Intelligence Laboratory, College of Computer ScienceSichuan UniversityChengduPeople’s Republic of China

Personalised recommendations