Advertisement

Deep Convolutional Neural Networks Based on Image Data Augmentation for Visual Object Recognition

  • Khaoula JayechEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11871)

Abstract

Deep Neural Networks (DNNs) have achieved a great success in machine learning. Among a lot of DNN structures, Deep Convolutional Neural Networks (DCNNs) are currently the main tool in the state-of-the-art variety of classification tasks like visual object recognition and handwriting and speech recognition. Despite wide perspectives, DCNNs have still some challenges to deal with. In previous work, we demonstrated the effectiveness of using some regularization techniques such as the dropout to enhance the performance of DCNNs. However, DCNNs need enough training data or even a class balance within datasets to conduct better results. To resolve this problem, some researchers have evoked different data augmentation approaches. This paper presents an extension of a later study. In this work, we conducted and compared the results of many experiments on CIFAR-10, STL-10 and SVHN using variant techniques of data augmentation combined with regularization techniques. The analysis results show that with the right use of data augmentation approaches, it is possible to achieve good results and outperform the state-of-the-art in this field.

Keywords

Deep learning DCNN Image data augmentation Object recognition 

References

  1. 1.
    Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: OverFeat: integrated recognition, localization and detection using convolutional networks. arXiv preprint arXiv:1312.6229 (2013)
  2. 2.
    Mellouli, D., Hamdani, T.M., Ayed, M.B., Alimi, A.M.: Morph-CNN: a morphological convolutional neural network for image classification. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, E.S. (eds.) Neural Information Processing, ICONIP 2017. LNCS, vol. 10635, pp. 110–117. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-70096-0_12CrossRefGoogle Scholar
  3. 3.
    Liang, Y., Yang, Y., Shen, F., Zhao, J., Zhu, T.: An incremental deep learning network for on-line unsupervised feature extraction. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, E.S. (eds.) International Conference on Neural Information Processing, vol. 10635, pp. 383–392. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-70096-0_40CrossRefGoogle Scholar
  4. 4.
    Liang, X., Wang, X., Lei, Z., Liao, S., Li, S.Z.: Soft-margin softmax for deep classification. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, E.S. (eds.) Neural Information Processing, ICONIP 2017. LNCS, vol. 10635, pp. 413–421. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-70096-0_43CrossRefGoogle Scholar
  5. 5.
    Zheng, Q., Yang, M., Yang, J., Zhang, Q., Zhang, X.: Improvement of generalization ability of deep CNN via implicit regularization in two-stage training process. IEEE Access 6, 15844–15869 (2018)CrossRefGoogle Scholar
  6. 6.
    Almodfer, R., Xiong, S., Mudhsh, M., Duan, P.: Very deep neural networks for hindi/arabic offline handwritten digit recognition. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, E.S. (eds.) International Conference on Neural Information Processing, ICONIP 2017. LNCS, vol. 10635, pp. 450–459. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-70096-0_47CrossRefGoogle Scholar
  7. 7.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436 (2015)CrossRefGoogle Scholar
  8. 8.
    Chen, W., Wilson, J., Tyree, S., Weinberger, K., Chen, Y.: Compressing neural networks with the hashing trick. In: International Conference on Machine Learning, pp. 2285–2294, June 2015Google Scholar
  9. 9.
    Liang, M., Hu, X.: Recurrent convolutional neural network for object recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3367–3375 (2015)Google Scholar
  10. 10.
    Tobías, L., Ducournau, A., Rousseau, F., Mercier, G., Fablet, R.: Convolutional neural networks for object recognition on mobile devices: a case study. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 3530–3535. IEEE, December 2016Google Scholar
  11. 11.
    Li, H., Xu, B., Wang, N., Liu, J.: Deep convolutional neural networks for classifying body constitution. In: Villa, A., Masulli, P., Pons Rivero, A. (eds.) International Conference on Artificial Neural Networks and Machine Learning – ICANN 2016. LNCS, vol. 9887, pp. 128–135. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-44781-0_16CrossRefGoogle Scholar
  12. 12.
    Devries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552 (2017)
  13. 13.
    Bai, S.: Growing random forest on deep convolutional neural networks for scene categorization. Expert Syst. Appl. 71, 279–287 (2017)CrossRefGoogle Scholar
  14. 14.
    Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)Google Scholar
  15. 15.
    He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026–1034 (2015)Google Scholar
  16. 16.
    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
  17. 17.
    Sun, Y., Chen, Y., Wang, X., Tang, X.: Deep learning face representation by joint identification-verification. In: Advances in Neural Information Processing Systems, pp. 1988–1996 (2014)Google Scholar
  18. 18.
    Taigman, Y., Yang, M., Ranzato, M.A., Wolf, L.: DeepFace: closing the gap to human-level performance in face verification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1701–1708 (2014)Google Scholar
  19. 19.
    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
  20. 20.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
  21. 21.
    Taylor, L., Nitschke, G.: Improving deep learning using generic data augmentation. arXiv preprint arXiv:1708.06020 (2017)
  22. 22.
    Jayech, K.: Regularized deep convolutional neural networks for feature extraction and classification. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, E.S. (eds.) Neural Information Processing. ICONIP 2017. LNCS, vol. 10635, pp. 431–439. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-70096-0_45CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Université de Sousse, Ecole Nationale d’Ingénieurs de Sousse, LATIS- Laboratory of Advanced Technology and Intelligent SystemsSousseTunisie

Personalised recommendations