Very Deep Neural Networks for Hindi/Arabic Offline Handwritten Digit Recognition

  • Rolla Almodfer
  • Shengwu Xiong
  • Mohammed Mudhsh
  • Pengfei DuanEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10635)


Handwritten Digit Recognition (HDR) has become one of the challenging areas of research in the field of document image processing during the last few decades. In this paper, inspired by the success of the very deep state-of-the-art VGGNet, we proposed VGG_No for HDR. VGG_No is fast and reliable, which improved the classification performance effectively. Besides, this model has also reduced the overall complexity of VGGNet. VGG_No constructed by thirteen convolutional layers, two max-pooling layers, and three fully connected layers. A Cross-Validation analysis has been performed using the 10-Fold Cross-Validation strategy, and 10-Fold classification accuracies of 99.57% and 99.69% have been obtained for ADBase database and MNIST database, respectively. The classification performance of VGG_No is superior to existing techniques using multi-classifiers since it has achieved better results using very simple and homogeneous architecture.


VGGNet Digit recognition ADBase MNIST 



This research was supported in part by Science & Technology Pillar Program of Hubei Province under Grant (#2014BAA146), Nature Science Foundation of Hubei Province under Grant (#2015CFA059), Science and Technology Open Cooperation Program of Henan Province under Grant (#152106000048).


  1. 1.
    Schantz, H.F.: The history of OCR. Recognition Technology Users Association, VT (1982)Google Scholar
  2. 2.
    Cosi, P.: Hybrid HMM-NN architectures for connected digit recognition. In: Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, IJCNN 2000, vol. 5 (2000)Google Scholar
  3. 3.
    Al-Haddad, S.A.R., Samad, S.A., Hussain, A., Ishak, K.A., Mirvaziri, H.: Decision fusion for isolated Malay digit recognition using dynamic time warping (DTW) and hidden Markov model (HMM). In: 5th Student Conference on Research and Development, SCOReD 2007, pp. 1–6. IEEE (2007)Google Scholar
  4. 4.
    Drewnik, M., Pasternak-Winiarski, Z.: SVM kernel configuration and optimization for the handwritten digit recognition. In: Saeed, K., Homenda, W., Chaki, R. (eds.) CISIM 2017. LNCS, vol. 10244, pp. 87–98. Springer, Cham (2017). doi: 10.1007/978-3-319-59105-6_8 CrossRefGoogle Scholar
  5. 5.
    Kim, E.H., Kim, B.Y., Oh, S.K.: Design of digits recognition system based on RBFNNs: a comparative study of pre-processing algorithms. Trans. Korean Inst. Electr. Eng. 66(2), 416–424 (2017)CrossRefGoogle Scholar
  6. 6.
    Summary by language size — ethnologue. Last accessed 25 Dec 2016
  7. 7.
    Mahmoud, S.: Recognition of writer-independent off-line handwritten Arabic (Indian) numerals using hidden Markov models. Signal Process. 88(4), 844–857 (2008)CrossRefzbMATHGoogle Scholar
  8. 8.
    Lécun, Y., Bottou, L., Bengio, Y.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRefGoogle Scholar
  9. 9.
    Hull, J.J.: A database for handwritten text recognition research. IEEE Trans. Pattern Anal. Mach. Intell. 16(5), 550–554 (1994)CrossRefGoogle Scholar
  10. 10.
    Al-Omari, F.A., Al-Jarrah, O.: Handwritten Indian numerals recognition system using probabilistic neural networks. Adv. Eng. Inf. 18(1), 9–16 (2004)CrossRefGoogle Scholar
  11. 11.
    Abdleazeem, S., El-Sherif, E.: Arabic handwritten digit recognition. Int. J. Doc. Anal. Recogn. (IJDAR) 11(3), 127–141 (2008)CrossRefGoogle Scholar
  12. 12.
    Parvez, M.T., Mahmoud, S.A.: Arabic handwritten alphanumeric character recognition using fuzzy attributed turning functions. In: Proceedings of the Workshop in Frontiers in Arabic Handwriting Recognition, 20th International Conference in Pattern Recognition (ICPR) (2012)Google Scholar
  13. 13.
    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
  14. 14.
    Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2015, pp. 1–9 (2015)Google Scholar
  15. 15.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2014). arXiv preprint: arXiv:1409.1556
  16. 16.
    Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2009), pp. 248–255 (2009)Google Scholar
  17. 17.
    Arabic Handwritten Digits Databases ADBase & MADBase. Last accessed 10 Aug 2017
  18. 18.
    The MNIST Database of Handwritten Digits. Last accessed 10 Aug 2017
  19. 19.
    Ciregan, D., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2012), pp. 3642–3649 (2012)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Rolla Almodfer
    • 1
  • Shengwu Xiong
    • 1
    • 2
  • Mohammed Mudhsh
    • 1
  • Pengfei Duan
    • 1
    • 2
    Email author
  1. 1.School of Computer Science and TechnologyWuhan University of TechnologyWuhanChina
  2. 2.Hubei Key Laboratory of Transportation Internet of ThingsWuhan University of TechnologyWuhanChina

Personalised recommendations