Advertisement

Evaluating Deep Convolutional Neural Networks as Texture Feature Extractors

  • Leonardo F. S. ScabiniEmail author
  • Rayner H. M. Condori
  • Lucas C. Ribas
  • Odemir M. Bruno
Conference paper
  • 425 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11752)

Abstract

Texture is an important visual property which has been largely employed for image characterization. Recently, Convolutional Networks has been the predominant approach on Computer Vision, and their application on texture analysis shows interesting results. However, their popularity steers around object recognition, and several convolutional architectures have been proposed and trained for this task. Therefore, this works evaluates 17 of the most diffused Deep Convolutional Neural Networks when employed for texture analysis as feature extractors. Image descriptors are obtained through Global Average Pooling over the output of the last convolutional layer of networks with random weights or learned from the ImageNet dataset. The analysis is performed under 6 texture datasets and using 3 different supervised classifiers (KNN, LDA, and SVM). Results using networks with random weights indicates that the architecture alone plays an important role in texture characterization, and it can even provide useful features for classification for some datasets. On the other hand, we found that although ImageNet weights usually provide the best results it can also perform similar to random weights in some cases, indicating that transferring convolutional weights learned on ImageNet may not always be appropriate for texture analysis. When comparing the best models, our results corroborate that DenseNet presents the highest overall performance while keeping a significantly small number of hyperparameters, thus we recommend its use for texture characterization.

Keywords

Deep Convolutional Neural Networks Texture analysis Feature extraction 

Notes

Acknowledgements

L. F. S. Scabini acknowledges support from CNPq (grant #142438/2018-9) and the São Carlos Institute of Physics (CAPES funding). R. H. M. Condori acknowledges support from FONDECYT, an initiative of the National Council of Science, Technology and Technological Innovation-CONCYTEC (Peru). L. C. Ribas gratefully acknowledges the financial support grant #s 2016/23763-8 and 2019/03277-0, São Paulo Research Foundation (FAPESP). O. M. Bruno acknowledges support from CNPq (grants #307797/2014-7 and #484312/2013-8) and FAPESP (grants #14/08026-1 and #16/18809-9). The authors are also grateful to the NVIDIA GPU Grant Program for the donation of the Quadro P6000 and the Titan Xp GPUs used on this research.

References

  1. 1.
    Abdelmounaime, S., Dong-Chen, H.: New Brodatz-based image databases for grayscale color and multiband texture analysis. ISRN Mach. Vis. 2013, 14 (2013)Google Scholar
  2. 2.
    Backes, A.R., Casanova, D., Bruno, O.M.: Color texture analysis based on fractal descriptors. Pattern Recogn. 45(5), 1984–1992 (2012)CrossRefGoogle Scholar
  3. 3.
    Cimpoi, M., Maji, S., Kokkinos, I., Vedaldi, A.: Deep filter banks for texture recognition, description, and segmentation. Int. J. Comput. Vis. 118(1), 65–94 (2016)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Csurka, G., Dance, C., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: Workshop on Statistical Learning in Computer Vision, ECCV, Prague, vol. 1, pp. 1–2 (2004)Google Scholar
  5. 5.
    Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 248–255. IEEE (2009)Google Scholar
  6. 6.
    Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 249–256 (2010)Google Scholar
  7. 7.
    He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), ICCV 2015, pp. 1026–1034. IEEE Computer Society, Washington, DC (2015)Google Scholar
  8. 8.
    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
  9. 9.
    Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)Google Scholar
  10. 10.
    Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)Google Scholar
  11. 11.
    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
  12. 12.
    LeCun, Y., et al.: Handwritten digit recognition with a back-propagation network. In: Advances in Neural Information Processing Systems, pp. 396–404 (1990)Google Scholar
  13. 13.
    Leung, T., Malik, J.: Representing and recognizing the visual appearance of materials using three-dimensional textons. Int. J. Comput. Vis. 43(1), 29–44 (2001)CrossRefGoogle Scholar
  14. 14.
    Lin, M., Chen, Q., Yan, S.: Network in network. arXiv preprint arXiv:1312.4400 (2013)
  15. 15.
    Liu, C., et al.: Progressive neural architecture search. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 19–35. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01246-5_2CrossRefGoogle Scholar
  16. 16.
    Liu, L., Chen, J., Fieguth, P., Zhao, G., Chellappa, R., Pietikäinen, M.: From BoW to CNN: two decades of texture representation for texture classification. Int. J. Comput. Vis. 127(1), 74–109 (2019)CrossRefGoogle Scholar
  17. 17.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)CrossRefGoogle Scholar
  18. 18.
    Ojala, T., Maenpaa, T., Pietikainen, M., Viertola, J., Kyllonen, J., Huovinen, S.: Outex-new framework for empirical evaluation of texture analysis algorithms. In: Proceedings of the 16th International Conference on Pattern Recognition, vol. 1, pp. 701–706. IEEE (2002)Google Scholar
  19. 19.
    Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Anal. Mach. Intell. 24(7), 971–987 (2002)CrossRefGoogle Scholar
  20. 20.
    Pickard, R., Graszyk, C., Mann, S., Wachman, J., Pickard, L., Campbell, L.: VisTex Database. MIT Media Lab, Cambridge (1995)Google Scholar
  21. 21.
    Saxe, A.M., Koh, P.W., Chen, Z., Bhand, M., Suresh, B., Ng, A.Y.: On random weights and unsupervised feature learning. In: ICML, vol. 2, p. 6 (2011)Google Scholar
  22. 22.
    Scabini, L.F., Condori, R.H., Gonçalves, W.N., Bruno, O.M.: Multilayer complex network descriptors for color-texture characterization. Inf. Sci. 491, 30–47 (2019)MathSciNetCrossRefGoogle Scholar
  23. 23.
    Schmidt, W.F., Kraaijveld, M.A., Duin, R.P.W.: Feedforward neural networks with random weights. In: Proceedings of the 11th IAPR International Conference on Pattern Recognition, Conference B: Pattern Recognition Methodology and Systems, vol. II, pp. 1–4 (1992)Google Scholar
  24. 24.
    Sharan, L., Rosenholtz, R., Adelson, E.: Material perception: what can you see in a brief glance? J. Vis. 9, 784 (2009)CrossRefGoogle Scholar
  25. 25.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  26. 26.
    Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, Inception-ResNet and the impact of residual connections on learning. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)Google Scholar
  27. 27.
    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016Google Scholar
  28. 28.
    Varma, M., Zisserman, A.: A statistical approach to texture classification from single images. Int. J. Comput. Vis. 62(1), 61–81 (2005)CrossRefGoogle Scholar
  29. 29.
    Xie, S., Girshick, R., Dollár, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492–1500 (2017)Google Scholar
  30. 30.
    Zhang, H., Xue, J., Dana, K.: Deep TEN: texture encoding network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 708–717 (2017)Google Scholar
  31. 31.
    Zhang, X., Li, Z., Change Loy, C., Lin, D.: PolyNet: a pursuit of structural diversity in very deep networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 718–726 (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Leonardo F. S. Scabini
    • 1
    Email author
  • Rayner H. M. Condori
    • 2
  • Lucas C. Ribas
    • 2
  • Odemir M. Bruno
    • 1
  1. 1.São Carlos Institute of PhysicsUniversity of São PauloSão CarlosBrazil
  2. 2.Institute of Mathematics and Computer ScienceUniversity of São PauloSão CarlosBrazil

Personalised recommendations