Deep Residual SENet for Foliage Recognition

  • Wensheng YanEmail author
  • Youqing Hua
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11782)


Foliage morphological features are important for plant recognition. However, the foliage shape generally presents big intra-class variations and small inter-class differences. This brings a great challenge to accurate plant foliage recognition. In this paper, we propose a deep residual squeeze-excitation network (R-SENet) for foliage recognition. Firstly, R-SENet learns and obtains the significance levels of each channel of the various convolutional layers in a residual block to recognition tasks via squeeze-excitation strategy. Then, the weights of each channel are rescaled by means of the significances to promote the relevant channels and inhibit non-important channels. Finally, we evaluate the proposed approach on the well-known Flavia dataset for foliage recognition. The experimental results indicate that our approach achieves more accurate average recognition rate (up to 97.86%) and more robustness to noise than other outstanding approaches.


Foliage recognition Residual network Squeeze-excitation network (SENet) Rescale weight 



This work was supported by the Major Special Project of Taizhou Vocational and Technical College under Grant No. 2019HGZ02, the Taizhou Science and Technology Project under Grant No. 1902gy31, and the Research Project of Teaching Reform of Zhejiang Province under Grant No. jg20190884.


  1. 1.
    Zhang, S., Wang, H., Huang, W.: Two-stage plant species recognition by local means clustering and weighted sparse representation classification. Cluster Comput. 20(2), 1517–1525 (2017)CrossRefGoogle Scholar
  2. 2.
    Lee, S., Chan, C., Mayo, S., Remagnino, P.: How deep learning extracts and learns foliage features for plant classification. Pattern Recogn. 71, 1–13 (2017)CrossRefGoogle Scholar
  3. 3.
    Fu, B., Yang, Z., Zhao, X.L., Shan, Z.L.: Plant leaves recognition method based on dimension reduction local binary pattern and shape features of leaves. Comput. Eng. Appl. 31(11), 3075–3077 (2011). (Chinese)Google Scholar
  4. 4.
    Oide, M., Ninomiya, S.: Discrimination of soybean foliagelet shape by neural networks with image input. Comput. Electron. Agric. 29(1), 59–72 (2000)CrossRefGoogle Scholar
  5. 5.
    Zhai, C.M., Wang, Q.P., Du, J.X.: Plant leaf recognition method based on fractal dimension feature of outline and venation. Comput. Sci. 41(2), 170–173 (2014). (Chinese)Google Scholar
  6. 6.
    Chen, L.X., Wang, B.: Comparative study of leaf image recognition algorithm based on shape feature. Comput. Eng. Appl. 53(9), 17–25 (2017). (Chinese)MathSciNetGoogle Scholar
  7. 7.
    Wang, B., Chen, L.X., Ye, M.J.: Chord-features matrices: an effective shape descriptor for plant leaf classification and retrieval. Chin. J. Comput. 40(11), 2559–2574 (2017)Google Scholar
  8. 8.
    Cope, J.S., Remagnino, P., Barman, S., Wilkin, P.: Plant texture classification using gabor co-occurrences. In: Bebis, G., et al. (eds.) ISVC 2010. LNCS, vol. 6454, pp. 669–677. Springer, Heidelberg (2010). Scholar
  9. 9.
    Zhang, C., Zhou, P., Li, C., Liu, L.: A convolutional neural network for foliages recognition using data augmentation. In: IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications, pp. 2143–2150 (2015)Google Scholar
  10. 10.
    Lee, S.H., Chan, C.S., Wilkin, P., Remagnino, P.: Deep-plant: plant recognition with convolutional neural networks. In: IEEE International Conference on Image Processing (ICIP), Canada, pp. 452–456 (2015)Google Scholar
  11. 11.
    Sugata, T.L.I., Yang, C.K.: Foliage App: foliage recognition with deep convolutional neural networks. IOP Conf. Ser.: Mater. Sci. Eng. 273(1), 012004 (2017)CrossRefGoogle Scholar
  12. 12.
    Kumar, N., et al.: Leafsnap: a computer vision system for automatic plant species identification. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7573, pp. 502–516. Springer, Heidelberg (2012). Scholar
  13. 13.
    Hall, D., Mccool, C., Dayoub, F., Sunderhauf, N., Upcroft, B.: Evaluation of features for foliage classification in challenging conditions. In: IEEE Winter Conference on Applications of Computer Vision, USA, Waikoloa, pp. 797–804 (2015)Google Scholar
  14. 14.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)Google Scholar
  15. 15.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  16. 16.
    Szegedy, C., et al.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), USA, Boston, pp. 1–9 (2015)Google Scholar
  17. 17.
    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818–2826 (2016)Google Scholar
  18. 18.
    Bell, S., Zitnick, C., Bala, K., Girshick, R.: Inside-outside net: detecting objects in context with skip pooling and recurrent neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2874–2883 (2016)Google Scholar
  19. 19.
    Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. arXiv preprint arXiv:1709.01507 (2017)
  20. 20.
    Jia, Y., Shelhamer, E., Donahue, J., et al.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM International Conference on Multimedia, USA, Orlando, pp. 675–678 (2014)Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2020

Authors and Affiliations

  1. 1.School of Information Technology EngineeringTaizhou Vocational and Technical CollegeTaizhouChina
  2. 2.School of Information EngineeringJinhua Vocational and Technical CollegeJinhuaChina

Personalised recommendations