Skip to main content

Advertisement

Springer Nature Link
Log in

Transformation-invariant Gabor convolutional networks

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

Although deep convolutional neural networks (DCNNs) have powerful capability of learning complex feature representations, they are limited by poor ability in handling large rotations and scale transformations. In this paper, we propose a novel alternative to conventional convolutional layer named Gabor convolutional layer (GCL) to enhance the robustness to transformations. The GCL is a simple but efficient combination of Gabor prior knowledge and parameters learning. A GCL is composed of three components: Gabor extraction module, weight-sharing convolution module, and transformation pooling module, respectively. DCNNs integrated with GCLs, referred to as transformation-invariant Gabor convolutional networks (TI-GCNs), can be easily built by replacing standard convolutional layers with designed GCLs. Our experimental results on various real-world recognition tasks indicate that encoding traditional hand-crafted Gabor filters with dominant orientation and scale information into DCNNs is of great importance for learning compact feature representations and reinforcing the resistance to scale changes and orientation variations. The source code can be found at https://github.com/GuichenLv.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

References

  1. Baochang, Z., Shiguang, S., Xilin, C., Wen, G.: Histogram of gabor phase patterns (hgpp): a novel object representation approach for face recognition. IEEE Trans. Image Process. 16(1), 57–68 (2007)

    Article  MathSciNet  Google Scholar 

  2. Boureau, Y.L., Ponce, J., LeCun, Y.: A theoretical analysis of feature pooling in visual recognition. In: Proceedings of the 27th International Conference on Machine Learning, pp. 111–118 (2010)

  3. Chai, Z., Sun, Z., Mendezvazquez, H., He, R., Tan, T.: Gabor ordinal measures for face recognition. IEEE Trans. Inf. Forensics Secur. 9(1), 14–26 (2014)

    Article  Google Scholar 

  4. Chang, S.Y., Morgan, N.: Robust CNN-based speech recognition with Gabor filter kernels. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, pp. 905–909 (2014)

  5. Chen, Y., Zhu, L., Ghamisi, P., Jia, X., Li, G., Tang, L.: Hyperspectral images classification with Gabor filtering and convolutional neural network. IEEE Geosci. Remote Sens. Lett. 14(12), 2355–2359 (2017)

    Article  Google Scholar 

  6. Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., Wei, Y.: Deformable convolutional networks. In: The IEEE International Conference on Computer Vision (ICCV) (2017)

  7. Daugman, J.: Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. J. Opt. Soc. Am. A-Opt. Image Sci. Vis. 2(7), 1160–1169 (1985)

    Article  Google Scholar 

  8. van Dyk, D.A., Meng, X.L.: The art of data augmentation. J. Comput. Graph. Stat. 10(1), 1–50 (2001)

    Article  MathSciNet  Google Scholar 

  9. Gabor, D.: Theory of communication. Part 1: the analysis of information. J. Inst. Electr. Eng. III Radio Commun. Eng. 93(26), 429–441 (1946)

    Google Scholar 

  10. Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer networks. In: Advances in Neural Information Processing Systems, pp. 2017–2025 (2015)

  11. Jiang, C., Su, J.: Gabor binary layer in convolutional neural networks. In: 2018 25th IEEE International Conference on Image Processing (ICIP), pp 3408–3412 (2018)

  12. Kanazawa, A., Sharma, A., Jacobs, D.: Locally scale-invariant convolutional neural networks. arXiv preprint arXiv:1412.5104 (2014)

  13. Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Technical Report, University of Toronto, Toronto, ON, Canada (2009)

  14. Laptev, D., Savinov, N., Buhmann, J.M., Pollefeys, M.: Ti-pooling: transformation-invariant pooling for feature learning in convolutional neural networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)

  15. Lenc, K., Vedaldi, A.: Understanding image representations by measuring their equivariance and equivalence. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)

  16. Liu, C., Wechsler, H.: Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition. IEEE Trans. Image Process. 11(4), 467–476 (2002)

    Article  Google Scholar 

  17. Liu, C.L., Nakashima, K., Sako, H., Fujisawa, H.: Handwritten digit recognition: benchmarking of state-of-the-art techniques. Pattern Recognit. 36(10), 2271–2285 (2003)

    Article  Google Scholar 

  18. Luan, S., Chen, C., Zhang, B., Han, J., Liu, J.: Gabor convolutional networks. IEEE Trans. Image Process. 27(9), 4357–4366 (2018)

    Article  MathSciNet  Google Scholar 

  19. Ma, Y., Luo, Y., Yang, Z.: Geometric operator convolutional neural network. arXiv preprint arXiv:1809.01016 (2018)

  20. Marcos, D., Kellenberger, B., Lobry, S., Tuia, D.: Scale equivariance in CNNs with vector fields. arXiv preprint arXiv:1807.11783 (2018)

  21. Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning. In: NIPS Workshop on Deep Learning and Unsupervised Feature Learning (2011)

  22. Shen, X., Tian, X., He, A., Sun, S., Tao, D.: Transform-invariant convolutional neural networks for image classification and search. In: Proceedings of the 24th ACM International Conference on Multimedia, pp. 1345–1354 (2016)

  23. Sohn, K., Lee, H.: Learning invariant representations with local transformations. arXiv preprint arXiv:1206.6418 (2012)

  24. Wang, Q., Zheng, Y., Yang, G., Jin, W., Chen, X., Yin, Y.: Multiscale rotation-invariant convolutional neural networks for lung texture classification. IEEE J. Biomed. Health Inform. 22(1), 184–195 (2018)

    Article  Google Scholar 

  25. Worrall, D.E., Garbin, S.J., Turmukhambetov, D., Brostow, G.J.: Harmonic networks: dep translation and rotation equivariance. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)

  26. Zhang, X., Liu, L., Xie, Y., Chen, J., Wu, L., Pietikainen, M.: Rotation invariant local binary convolution neural networks. In: The IEEE International Conference on Computer Vision (ICCV) Workshops (2017)

  27. Zhou, Y., Ye, Q., Qiu, Q., Jiao, J.: Oriented response networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)

Download references

Acknowledgements

This work is supported by the Shenzhen Science and Technology Innovation Committee (STIC) under Grant JCYJ20180306174455080.

Author information

Authors and Affiliations

  1. The School of Automation, Southeast University, Nanjing, China

    Lei Zhuang, Feipeng Da & Shaoyan Gai

  2. The Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Nanjing, China

    Lei Zhuang, Feipeng Da & Shaoyan Gai

  3. Shenzhen Research Institute, Southeast University, Shenzhen, China

    Feipeng Da

  4. The National Research Center of Overseas Sinology, Beijing Foreign Studies University, Beijing, China

    Mengxiang Li

Authors
  1. Lei Zhuang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Feipeng Da
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Shaoyan Gai
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Mengxiang Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Feipeng Da.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhuang, L., Da, F., Gai, S. et al. Transformation-invariant Gabor convolutional networks. SIViP 14, 1413–1420 (2020). https://doi.org/10.1007/s11760-020-01684-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11760-020-01684-6

Keywords