Recognizing Digits from Natural Images and handwritten Digits using Deep Convolutional Neural Networks

Authors(2) :-Rohit Thapa, Dhrub Kumar

Recognizing digits from Natural Images and Handwritten digits are one of the famous problems in Computer Vision Applications.Many Machine Learning Techniques have been employed to solve the problem of recognizing Digits from Natural Images and Handwritten Digits.The most three famous NN approaches are deep neural network (DNN), deep belief network (DBN) and convolutional neural network (CNN). This Paper focuses on Convolutional Neural Networks (CNN), also known as Deep Convolutional Neural Network (DCNN) that operates directly on image pixels, also the three NN approaches are compared and evaluated in terms of many factors such as accuracy and performance. Recognition accuracy rate and performance, however, is not the only criterion in the evaluation process, but there are interesting criteria such as execution time. In addition, DistBelief [15] implementation of deep neural network is employed to train large & distributed neural networks on high quality images. At the end, we find that the performance of this approach increases with the depth of the convolutional network. With the best performance occurring in the deepest architecture with eleven hidden layers. We evaluate this approach on the publically available SVHN dataset and achieve over 96% accuracy in recognizing complete street numbers. This paper also presents blocky artifact as an augmentation technique to increase the accuracy of DCNN for handwritten digit recognition i.e 0-9 and conducts experiments on MNIST dataset only. DCNNs with the proposed augmentation technique give better results than those without such augmentation.

Authors and Affiliations

Rohit Thapa
Department of Information Technology, Model Institute of Engineering & Technology, Kot Bhalwal, Jammu, India
Dhrub Kumar
Department of Information Technology, Model Institute of Engineering & Technology, Kot Bhalwal, Jammu, India

DistBelief, SVHN, MNIST, Blocky Artifact, Augmentation

  1. Y. LeCun, C. Cortes, and C. J. Burges, The mnist database of handwritten digits, 1998.
  2. D. C. Ciresan, U. Meier, L. M. Gambardella, and J. Schmidhuber, Deep, big, simple neural nets for handwritten digit recognition, Neural computation, vol. 22, no. 12, pp. 32073220, 2010.
  3. R. Wu, S. Yan, Y. Shan, Q. Dang, and G. Sun, Deep image: Scaling up image recognition, arXiv preprint arXiv:1501.02876, vol. 7, no. 8, 2015.
  4. M. Shopon, N. Mohammed, and A. Abedin, Bangla handwritten digit recognition using auto encoder and deep convolutional neural network, in International Workshop on Computational Intelligence, 2016, accepted and Presented.
  5. Python scikit-image,, accessed: 2016-12-26.
  6. M. Liang and X. Hu, Recurrent convolutional neural network for object recognition, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 33673375.
  7. C.-Y. Lee, P. W. Gallagher, and Z. Tu, Generalizing pooling functions in convolutional neural networks: Mixed, gated, and tree, in International Conference on Artificial Intelligence and Statistics, 2016.
  8. J.-R. Chang and Y.-S. Chen, Batch-normalized maxout network in network, arXiv preprint arXiv:1511.02583, 2015.
  9. Sato, H. Nishimura, and K. Yokoi, Apac: Augmented pattern classification with neural networks, arXiv preprint arXiv:1505.03229, 2015.
  10. D. Ciregan, U. Meier, and J. Schmidhuber, Multi-column deep neural networks for image classification, in Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, 2012, pp. 3642 3649.
  11. L. Wan, M. Zeiler, S. Zhang, Y. L. Cun, and R. Fergus, Regularization of neural networks using dropconnect, in Proceedings of the 30th International Conference on Machine Learning (ICML-13), 2013, pp. 10581066.
  12. Buntine, W. (1994). Operations for learning with graphical models. Journal of Artificial Intelligence Research, 2, 159225.
  13. Fukushima, K. (1980). Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological Cybernetics, 36, 193202.
  14. Goodfellow, I. J., Warde-Farley, D., Mirza, M., Courville, A., and Bengio, Y. (2013). Maxout networks. In ICML2013.
  15. Dean, J., Corrado, G., Monga, R., Chen, K., Devin, M., Le, Q., Mao, M.,
  16. Ranzato, M., Senior, A., Tucker, P., Yang, K., and Ng, A. Y. (2012). Large scale distributed deep networks. In NIPS2012.
  17. Sermanet, P., Chintala, S., and LeCun, Y. (2012). Convolutional neural networks applied to house numbers digit classification. In International Conference on Pattern Recognition (ICPR 2012).
  18. Hyvarinen, A., Karhunen, J., and Oja, E. (2001). ¨ Independent Component Analysis. Wiley-Interscience.
  19. Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., and Ng, A. Y. (2011). Reading digits in natural images with unsupervised feature learning. Deep Learning and Unsupervised Feature Learning Workshop, NIPS.

Publication Details

Published in : Volume 4 | Issue 1 | March-April 2018
Date of Publication : 2018-04-25
License:  This work is licensed under a Creative Commons Attribution 4.0 International License.
Page(s) : 158-165
Manuscript Number : CSEIT411827
Publisher : Technoscience Academy

ISSN : 2456-3307

Cite This Article :

Rohit Thapa, Dhrub Kumar, "Recognizing Digits from Natural Images and handwritten Digits using Deep Convolutional Neural Networks", International Journal of Scientific Research in Computer Science, Engineering and Information Technology (IJSRCSEIT), ISSN : 2456-3307, Volume 4, Issue 1, pp.158-165, March-April-2018.
Journal URL :

Article Preview