Simplistic Deep Learning for Japanese Handwritten Digit Recognition

  • Arkadip Ghosh
  • Aishwarjyamoy Mukherjee
  • Chinmoy GhoshEmail author
Conference paper
Part of the Learning and Analytics in Intelligent Systems book series (LAIS, volume 12)


We show a simplistic approach using simple Convolutional Neural Network (CNN) to classify Japanese handwritten digit dataset Kuzushiji-MNIST. We use combinations of loss functions and optimisers on an empirically sound model of Convolutional Neural Netwok (CNN) to come up with a new State-of-the-art accuracy for all Simple CNN approaches on the Kuzushiji-MNIST dataset with accuracy of 96.13 %.


Convolutional Neural Netwok (CNN) Kuzushiji-MNIST Optimizer Loss function Adam Categorical crossentropy 


  1. 1.
    Clanuwat, T., Bober-Irizar, M., Kitamoto, A., Lamb, A., Yamamoto, K., Ha, D.: Deep Learning for Classical Japanese Literature. Cornell University (2018)Google Scholar
  2. 2.
    Chollet, F., et al.: Keras (2015).
  3. 3.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)Google Scholar
  4. 4.
    Deng, L.: The MNIST database of handwritten digit images for machine learning research [best of the web]. IEEE Signal Process. Mag. 29(6), 141–142 (2012)CrossRefGoogle Scholar
  5. 5.
    Kussul, E., Baidyk, T.: Improved method of handwritten digit recognition tested on MNIST database. Image Vis. Comput. 22(12), 971–981 (2004)CrossRefGoogle Scholar
  6. 6.
    Keysers, D.: Comparison and combination of state-of-the-art techniques for handwritten character recognition: topping the MNIST Benchmark (2007)Google Scholar
  7. 7.
  8. 8.
    Hidasi, B., Karatzoglou, A.: Recurrent neural networks with top-k gains for session-based recommendations. In: Proceedings of the 27th ACM International Conference on Information and Knowledge Management, pp. 843–852, October 2018Google Scholar
  9. 9.
    Tsai, C.: Recognizing handwritten Japanese characters using deep convolutional neural networks. University of Stanford in Stanford, California (2016)Google Scholar
  10. 10.
    Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving neural networks by preventing co-adaptation of feature detectors (2012)Google Scholar
  11. 11.
    Uchida, S., Ide, S., Iwana, B.K., Zhu, A.: A further step to perfect accuracy by training CNN with larger data. In: International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 405–410. IEEE (2016)Google Scholar
  12. 12.
    Wan, L., Zeiler, M., Zhang, S., Le Cun, Y., Fergus, R.: Regularization of neural networks using dropconnect. In: International Conference on Machine Learning, pp. 1058–1066 (2013)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Arkadip Ghosh
    • 1
  • Aishwarjyamoy Mukherjee
    • 1
  • Chinmoy Ghosh
    • 1
    Email author
  1. 1.Department of Computer Science and EngineeringJalpaiguri Government Engineering College (Autonomous)JalpaiguriIndia

Personalised recommendations