Examination of the Deep Neural Networks in Classification of Distorted Signals

  • Michał KoziarskiEmail author
  • Bogusław Cyganek
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9693)


Classification of distorted patterns poses real problem for majority of classifiers. In this paper we analyse robustness of deep neural network in classification of such patterns. Using specific convolutional network architecture, an impact of different types of noise on classification accuracy is evaluated. For highly distorted patterns to improve accuracy we propose a preprocessing method of input patterns. Finally, an influence of different types of noise on classification accuracy is also analysed.


Noise Image recognition Convolutional neural networks 



This work was supported by the Polish National Science Centre under the grant no. DEC-2014/15/B/ST6/00609.


  1. 1.
    Bovik, A.C.: Handbook of Image and Video Processing. Academic Press, Cambridge (2010)zbMATHGoogle Scholar
  2. 2.
    Cyganek, B., Siebert, J.P.: An Introduction to 3D Computer Vision Techniques and Algorithms. Wiley, Hoboken (2011)zbMATHGoogle Scholar
  3. 3.
    Bengio, Y., Goodfellow, I.J., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)Google Scholar
  4. 4.
    Stallkamp, J., Schlipsing, M., Salmen, J., Igel, C.: Man vs. computer: benchmarking machine learning algorithms for traffic sign recognition. Neural Netw. 32, 323–332 (2012)CrossRefGoogle Scholar
  5. 5.
    Cireşan, D., Meier, U., Masci, J., Schmidhuber, J.: Multi-column deep neural network for traffic sign classification. Neural Netw. 32, 333–338 (2012)CrossRefGoogle Scholar
  6. 6.
    Sermanet, P., LeCun, Y.: Traffic sign recognition with multi-scale convolutional networks. In: The 2011 International Joint Conference on Neural Networks, pp. 2809–2813 (2011)Google Scholar
  7. 7.
    Zaklouta, F., Stanciulescu, B., Hamdoun, O.: Traffic sign classification using K-d trees and random forests. In: The 2011 International Joint Conference on Neural Networks, pp. 2151–2155 (2011)Google Scholar
  8. 8.
    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
  9. 9.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  10. 10.
    Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning, pp. 807–814 (2010)Google Scholar
  11. 11.
    Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)MathSciNetzbMATHGoogle Scholar
  12. 12.
    Eigen, D., Krishnan, D., Fergus, R.: Restoring an image taken through a window covered with dirt or rain. In: 2013 IEEE International Conference on Computer Vision, pp. 633–640 (2013)Google Scholar
  13. 13.
    Jain, V., Seung, S.: Natural image denoising with convolutional networks. In: Advances in Neural Information Processing Systems, pp. 769–776 (2009)Google Scholar
  14. 14.
    Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)CrossRefGoogle Scholar
  15. 15.
    Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., Ghemawat, S.: TensorFlow: large-scale machine learning on heterogeneous systems (2015).

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Wrocław University of TechnologyWrocławPoland
  2. 2.AGH University of Science and TechnologyKrakówPoland

Personalised recommendations