Advertisement

Convolutional Neural Network for Machine-Printed Traditional Mongolian Font Recognition

  • Hongxi Wei
  • Ya Wen
  • Weiyuan Wang
  • Guanglai Gao
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11305)

Abstract

Although font recognition is a fundamental issue in the field of document analysis and recognition, it was usually ignored in the past. With the development of optical character recognition (OCR), font recognition becomes more and more important. This paper proposed a well-designed convolutional neural network (CNN) architecture for traditional Mongolian font recognition by means of a single word. To be specific, the whole word image is regarded as input of CNN. Hence, the word images should be normalized into the same size before being inputted into CNN. By comparison, an appropriate aspect ratio for the traditional Mongolian word images has been determined. Experimental results demonstrate that the proposed CNN architecture outperforms three classic CNN architectures, including LeNet-5, AlexNet and GoogLeNet. Therefore, the proposed CNN is much more suitable for the task of the traditional Mongolian font recognition in the way of a single word.

Keywords

Traditional Mongolian Font recognition Convolutional neural network Word image Aspect ratio 

Notes

Acknowledgements

This paper is supported by the National Natural Science Foundation of China under Grant 61463038.

References

  1. 1.
    Zramdini, A., Ingold, R.: Optical font recognition using typographical features. IEEE Trans. Pattern Anal. Mach. Intell. 20(8), 877–882 (1998)CrossRefGoogle Scholar
  2. 2.
    Jung, M., Shin, Y., Srihari, N.: Multifont classification using typographical attributes. In: Proceedings of ICDAR 1999, pp. 353–356. IEEE Press, New York (1999)Google Scholar
  3. 3.
    Moussa, B., Zahour, A., Benabdelhafid, A., Alimi, M.: New features using fractal multi-dimensions for generalized Arabic font recognition. Pattern Recogn. Lett. 31(5), 361–371 (2010)CrossRefGoogle Scholar
  4. 4.
    Lutf, M., You, X., Cheung, Y., Chen, P.: Arabic font recognition based on diacritics features. Pattern Recogn. 47(2), 672–684 (2014)CrossRefGoogle Scholar
  5. 5.
    Zhu, Y., Tan, T., Wang, Y.: Font recognition based on global texture analysis. IEEE Trans. Pattern Anal. Mach. Intell. 23(10), 1192–1200 (2001)CrossRefGoogle Scholar
  6. 6.
    Ding, Q., Li, C., Tao, W.: Character independent font recognition on a single Chinese character. IEEE Trans. Pattern Anal. Mach. Intell. 29(2), 195–204 (2007)CrossRefGoogle Scholar
  7. 7.
    Song, W., Lian, Z., Tang, Y., Xiao, J.: Content-independent font recognition on a single Chinese character using sparse representation. In: Proceedings of ICDAR 2015, pp. 376–380. IEEE Press, New York (2015)Google Scholar
  8. 8.
    Joshi, G., Garg, S., Sivaswamy, J.: A generalized framework for script identification. Int. J. Doc. Anal. Recogn. 10(2), 55–68 (2007)CrossRefGoogle Scholar
  9. 9.
    Tao, D., Lin, X., Jin, L., Li, X.: Principal component 2-D long short-term memory for font recognition on single Chinese characters. IEEE Trans. Cybern. 46(3), 756–765 (2016)CrossRefGoogle Scholar
  10. 10.
    Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. In: Proceedings of NIPS 2012, pp. 1097–1105. Curran Associates Inc. (2012)Google Scholar
  11. 11.
    Ciresan, D., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. In: Proceedings of CVPR 2012, pp. 3642–3649. IEEE Press, New York (2012)Google Scholar
  12. 12.
    Oquab, M., Bottou, L., Laptev, I., Sivic, J.: Learning and transferring mid-level image representations using convolutional neural networks. In: Proceedings of CVPR 2014, pp. 1717–1724. IEEE Press, New York (2014)Google Scholar
  13. 13.
    Gao, P., Gu, G., Wu, J., Wei, B.: Chinese calligraphic style representation for recognition. Int. J. Doc. Anal. Recogn. 20(1), 59–68 (2017)CrossRefGoogle Scholar
  14. 14.
    Tensmeyer, C., Saunders, D., Martinez, T.: Convolutional neural networks for font classification. In: Proceedings of ICDAR 2017, pp. 985–990. IEEE Press, New York (2017)Google Scholar
  15. 15.
    Wei, H., Gao, G.: A keyword retrieval system for historical Mongolian document images. Int. J. Doc. Anal. Recogn. 17(1), 33–45 (2014)CrossRefGoogle Scholar
  16. 16.
    Wei, H., Gao, G.: Machine-printed traditional Mongolian characters recognition using BP neural networks. In: Proceedings of CiSE 2009, pp. 1–7. IEEE Press, New York (2009)Google Scholar
  17. 17.
    Hu, H., Wei, H., Liu, Z.: The CNN based machine-printed traditional Mongolian characters recognition. In: Proceedings of CCC 2017, pp. 3937–3941. IEEE Press, New York (2017)Google Scholar
  18. 18.
    Zhang, H., Wei, H., Bao, F., Gao, G.: Segmentation-free printed traditional Mongolian OCR using sequence to sequence with attention model. In: Proceedings of ICDAR 2017, pp. 585–590. IEEE Press, New York (2017)Google Scholar
  19. 19.
    Ma, L., Liu, J., Wu, J.: A new database for online handwritten Mongolian word recognition. In: Proceedings of ICPR 2016, pp. 1131–1136. IEEE Press, New York (2016)Google Scholar
  20. 20.
    Hinton, G., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012)
  21. 21.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRefGoogle Scholar
  22. 22.
    Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S.: Going deeper with convolutions. In: Proceedings of CVPR 2015, pp. 1–9. IEEE Press, New York (2015)Google Scholar
  23. 23.
    Wei, H., Gao, G., Bao, Y.: A method for removing inflectional suffixes in word spotting of Mongolian Kanjur. In: Proceedings of ICDAR 2011, pp. 88–92. IEEE Press, New York (2011)Google Scholar
  24. 24.
    Wei, H., Zhang, H., Gao, G.: Representing word image using visual word embeddings and RNN for keyword spotting on historical document images. In: Proceedings of ICME 2017, pp. 1368–1373. IEEE Press, New York (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Hongxi Wei
    • 1
    • 2
  • Ya Wen
    • 1
    • 2
  • Weiyuan Wang
    • 1
    • 2
  • Guanglai Gao
    • 1
    • 2
  1. 1.School of Computer ScienceInner Mongolia UniversityHohhotChina
  2. 2.Provincial Key Laboratory of Mongolian Information Processing TechnologyHohhotChina

Personalised recommendations