Deep Convolutional Neural Networks and Noisy Images

  • Tiago S. Nazaré
  • Gabriel B. Paranhos da Costa
  • Welinton A. Contato
  • Moacir Ponti
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10657)


The presence of noise represent a relevant issue in image feature extraction and classification. In deep learning, representation is learned directly from the data and, therefore, the classification model is influenced by the quality of the input. However, the ability of deep convolutional neural networks to deal with images that have a different quality when compare to those used to train the network is still to be fully understood. In this paper, we evaluate the generalization of models learned by different networks using noisy images. Our results show that noise cause the classification problem to become harder. However, when image quality is prone to variations after deployment, it might be advantageous to employ models learned using noisy data.



The authors would like to thank FAPESP (grants #16/16111-4, #13/07375-0, #15/05310-3, #15/04883-0).


  1. 1.
    Arnold, T.: Stat 365/665: Data mining and machine learning: Lecture notes (transfer learning and computer vision I) (April 2016)Google Scholar
  2. 2.
    Bekker, A.J., Goldberger, J.: Training deep neural-networks based on unreliable labels. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2682–2686. IEEE (2016)Google Scholar
  3. 3.
    Buades, A., Coll, B., Morel, J.M.: A non-local algorithm for image denoising. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 2, pp. 60–65. IEEE (2005)Google Scholar
  4. 4.
    Paranhos da Costa, G.B., Contato, W.A., Nazare, T.S., Batista Neto, J.E.S., Ponti, M.: An empirical study on the effects of different types of noise in image classification tasks. In: XII Workshop de Visão Computacional (WVC 2016) (2016)Google Scholar
  5. 5.
    Dodge, S., Karam, L.: Understanding how image quality affects deep neural networks. In: 2016 Eighth International Conference on Quality of Multimedia Experience (QoMEX), pp. 1–6 (Jun 2016)Google Scholar
  6. 6.
    Ghifary, M., Kleijn, W.B., Zhang, M.: Deep hybrid networks with good out-of-sample object recognition. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5437–5441. IEEE (2014)Google Scholar
  7. 7.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385 (2015)
  8. 8.
    Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images (2009)Google Scholar
  9. 9.
    Kylberg, G., Sintorn, I.M.: Evaluation of noise robustness for local binary pattern descriptors in texture classification. EURASIP J. Image Video Process. 2013, 17 (2013)CrossRefGoogle Scholar
  10. 10.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRefGoogle Scholar
  11. 11.
    Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning (2011)Google Scholar
  12. 12.
    Ponti, M., Nazaré, T.S., Thumé, G.S.: Image quantization as a dimensionality reduction procedure in color and texture feature extraction. Neurocomputing 173, 385–396 (2016)CrossRefGoogle Scholar
  13. 13.
    Seltzer, M.L., Yu, D., Wang, Y.: An investigation of deep neural networks for noise robust speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 7398–7402. IEEE (2013)Google Scholar
  14. 14.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556 (2014)Google Scholar
  15. 15.
    Springenberg, J.T., Dosovitskiy, A., Brox, T., Riedmiller, M.: Striving for simplicity: the all convolutional net. arXiv preprint arXiv:1412.6806 (2014)

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Instituto de Ciências Matemáticas e de ComputaçãoUniversidade de São PauloSão CarlosBrazil

Personalised recommendations