Advertisement

Wavelet Convolutional Neural Networks for Handwritten Digits Recognition

  • Chiraz Ben Chaabane
  • Dorra Mellouli
  • Tarek M. Hamdani
  • Adel M. Alimi
  • Ajith Abraham
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 734)

Abstract

Image recognition is a very important subject in machine learning. With the increased use of intelligent applications, the image recognition has become more important in various domains. Thus, neural networks and deep learning algorithms has proved a notable success in the domain of image recognition and classification. Convolutional Neural Networks (CNN) are a class of deep learning methods. They are constrained from convolutional, pooling and fully connected layers. While they achieved great results in object recognition and classification, the pooling layer does not take into consideration the structure of the features. This paper emphasizes the pooling layer of CNN by adding a wavelet decomposition to obtain a new architecture called Wavelet Convolutional Neural Networks (WaveCNN). This architecture is validated on the handwritten digits recognition application using the MNIST benchmark. Compared to a conventional CNN with the same architecture, we found better results. Hence, WaveCNN is able to represent more adequately features for classification.

Keywords

Deep learning Convolutional neural networks Wavelet transform Wavelet convolutional neural networks 

References

  1. 1.
    Williams, T., Li, R.: SDA-based neural network approach to digit classification, May 2016Google Scholar
  2. 2.
    Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. In: Proceedings of the IEEE, vol. 86, pp. 2278–2324 (1998)Google Scholar
  3. 3.
    Chui, C.K.: An Introduction to Wavelets. Academic Press, New York (1992)zbMATHGoogle Scholar
  4. 4.
    Rieder, P., Gotze, J., Nossek, J.A.: Multiwavelet transforms based on several scaling functions. In: Proceedings IEEE International Symposium on Time-Frequency Time-Scale, October 1994Google Scholar
  5. 5.
    Alom, M.Z., Sidike, P., Taha, T.M., Asari, V.K.: Handwritten bangla digit recognition using deep learning, May 2017Google Scholar
  6. 6.
    Mallat, S.G.: A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans. Patt. Anal. Mach. Intell. 11, 674–693 (1989)CrossRefzbMATHGoogle Scholar
  7. 7.
    Burrus, C.S., Gonipath, R.A., Guo, H.: Introduction to wavelets and wavelet transforms: a primer. Prentice Hall, Englewood Cliffs (1998)Google Scholar
  8. 8.
    Sihag, R., Sharma, R., Setia, V.: Wavelet thresholding for image de-noising. In: International Conference on VLSI, Communication & Instrumentation, pp. 21–24 (2011)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Chiraz Ben Chaabane
    • 1
  • Dorra Mellouli
    • 1
  • Tarek M. Hamdani
    • 1
    • 2
  • Adel M. Alimi
    • 1
  • Ajith Abraham
    • 3
  1. 1.REGIM-Lab: REsearch Groups in Intelligent Machines, National Engineering School of SfaxUniversity of SfaxSfaxTunisia
  2. 2.College of Science and Arts at AI-UlaTaibah Universityal-Madinah al-MunawwarahKingdom of Saudi Arabia
  3. 3.Machine Intelligence Research Labs (MIR Labs)AuburnUSA

Personalised recommendations