Advertisement

Identification of Soybean Leaf Diseases via Deep Learning

  • Qiufeng WuEmail author
  • Keke Zhang
  • Jun Meng
Original Contribution
  • 85 Downloads

Abstract

We propose a novel approach for identifying soybean leaf diseases in the natural environment by convolutional neural network (CNN). AlexNet, GoogLeNet and ResNet were utilized for transfer learning. Firstly, 27 models were obtained by setting different batch sizes and the number of iterations. Then, the effects of CNN structure on identification performance were explored. The optimal model is based on ResNet and has the highest accuracy of 94.29%. In the parameter settings of the optimal network, the number of iterations and batch size are 1056 and 16, respectively, and the training depth is 140. Overall, the proposed method is effective for identifying soybean leaf diseases in the natural environment.

Keywords

Soybean leaf diseases Deep learning Convolutional neural network Image recognition 

Notes

Acknowledgements

This work was supported by the Public Welfare Industry (Agriculture) Research Projects Level-2 under Grant 201503116-04-06; Postdoctoral Foundation of Heilongjiang Province under Grant LBHZ15020; Harbin Applied Technology Research and Development Program under Grant 2017RAQXJ096; and National Key Application Research and Development Program in China under Grant 2018YFD0300105-2.

References

  1. 1.
    J. Meng, Q. Wu, The research of cyclic fluctuation rule and forming reason for soybean production of China. Ecol. Econ. (Acad. Edit.) 1, 175–178 (2008)Google Scholar
  2. 2.
    C. Zhao, X. Xue, X. Wang et al., Advance and prospects of precision agriculture technology system. Trans. Chin. Soc. Agric. Eng. 19(4), 7–12 (2003)Google Scholar
  3. 3.
    L. Guan, Z. Liu, Q. Wu et al., Multi-type feature fusion technique for weed identification in cotton fields. Int. J. Signal Process. Image Process. Pattern Recognit. 9(2), 355–368 (2016)Google Scholar
  4. 4.
    B. Cheng, E.T. Matson, A feature-based machine learning agent for automatic rice and weed discrimination, in AISC 2015 Conference Proceeding (2015), pp. 517–527CrossRefGoogle Scholar
  5. 5.
    X. Ma, H. Guan, G. Qi et al., Diagnosis model of soybean leaf diseases based on improved cascade neural network. Trans. Chin. Soc. Agric. Mach. 48(1), 163–168 (2017)Google Scholar
  6. 6.
    S. Vijai, A.K. Misra, Detection of plant leaf diseases using image segmentation and soft computing techniques. Inform. Process. Agric. 4, 41–49 (2017)Google Scholar
  7. 7.
    P.J. Herrera, J. Dorado, Á. Ribeiro, A novel approach for weed type classification based on shape descriptors and a fuzzy decision-making method. Sensors 14, 15304–15324 (2014)CrossRefGoogle Scholar
  8. 8.
    J. Deng, M. Li, Z. Yuan et al., Feature extraction and classification of Tilletia diseases based on image recognition. Trans. Chin. Soc. Agric. Eng. 28(3), 172–176 (2012)Google Scholar
  9. 9.
    Z. Liu, X. Xu, Q. Wu, A novel K-nearest neighbor algorithm based on I-divergence criterion. ICIC Express Lett. B: Appl. 4(2), 243–248 (2013)Google Scholar
  10. 10.
    X. Xu, Z. Liu, Q. Wu, A novel K-nearest neighbor classification algorithm based on maximum entropy. Int. J. Adv. Comput. Technol. 5(5), 966–973 (2013)Google Scholar
  11. 11.
    Y. Lecun, Y. Bengio, G. Hinton, Deep learning. Nature 521, 436–444 (2015)CrossRefGoogle Scholar
  12. 12.
    L. Zhang, F. Yang, Y.D. Zhang et al., Road crack detection using deep convolutional neural network, in ICIP 2016 Conference Proceeding (2016), pp. 3708–3712Google Scholar
  13. 13.
    Z. Zhou, J. Shin, L. Zhang et al., Fine-tuning convolutional neural networks for biomedical image analysis: actively and incrementally, in CVPR 2017 Conference Proceeding (2017), pp. 4761–4772Google Scholar
  14. 14.
    D. Xie, L. Zhang, L. Bai, Deep learning in visual computing and signal processing. Appl. Comput. Intell. Soft Comput. 10, 1–13 (2017)CrossRefGoogle Scholar
  15. 15.
    W. Ouyang, X. Wang, Joint deep learning for pedestrian detection, in ICCV2013 Conference Proceeding (2013), pp. 2056–2063Google Scholar
  16. 16.
    Z. Liu, P. Luo, X. Wang et al., Deep learning face attributes in the wild, in ICCV2015 Conference Proceeding (2015), pp. 3730–3738Google Scholar
  17. 17.
    X. Cheng, Y. Zhang, Y. Chen, Y. Wu, Y. Yue, Pest identification via deep residual learning in complex background. Comput. Electron. Agric. 141, 351–356 (2017)CrossRefGoogle Scholar
  18. 18.
    S.F. Alessandro, M.F. Daniela, G.S. Gercina, P. Hemerson, T.F. Marcelo, Weed detection in soybean crops using ConvNets. Comput. Electron. Agric. 143, 314–324 (2017)CrossRefGoogle Scholar
  19. 19.
    X. Deng, L. Qi, X. Ma et al., Recognition of weeds at seedling stage in paddy fields using multi-feature fusion and deep belief networks. Trans. Chin. Soc. Agric. Eng. 34(14), 165–172 (2018)Google Scholar
  20. 20.
    I. Sa, Z. Ge, F. Dayoub, B. Upcroft, T. Perez, C. McCool, DeepFruits: a fruit detection system using deep neural networks. Sensors 16, 1222 (2016)CrossRefGoogle Scholar
  21. 21.
    K. Zhang, Q. Wu, A. Liu, X. Meng, Can deep learning identify tomato leaf disease? Adv. Multimed. (2018).  https://doi.org/10.1155/2018/6710865 CrossRefGoogle Scholar
  22. 22.
    J. Ma, K. Du, F. Zheng et al., Disease recognition system for greenhouse cucumbers based on deep convolutional neural network. Trans. Chin. Soc. Agric. Eng. 34(12), 186–192 (2018)Google Scholar
  23. 23.
    S.P. Mohanty, D.P. Hughes, M. Salathé, Using deep learning for image-based plant disease detection. Front. Plant Sci. 7, 1419 (2016)CrossRefGoogle Scholar
  24. 24.
    A. Krizhevsky, I. Sutskever, G.E. Hinton, ImageNet classification with deep convolutional neural networks, in NIPS 2012 Conference Proceeding (2012), pp. 1097–1105Google Scholar
  25. 25.
    C. Szegedy, W. Liu, Y. Jia et al., Going deeper with convolutions, in CVPR 2015 Conference Proceeding (2015). http://dx.doi.org/10.1109/cvpr.2015.7298594
  26. 26.
    K. He, X. Zhang, S. Ren et al., Deep residual learning for image recognition, in CVPR 2016 Conference Proceeding (2016), pp. 770–778Google Scholar
  27. 27.
    V. Nair, G.E. Hinton, Rectified linear units improve restricted boltzmann machines, in ICML 2010 Conference Proceeding (2010), pp. 807–814Google Scholar
  28. 28.
    M. Lin, Q. Chen, S. Yan, Network in Network (2014). arXiv:1312.4400v3
  29. 29.
    K. He, X. Zhang, S. Ren et al., Identity Mappings in Deep Residual Networks (2016). arXiv:1603.05027v3
  30. 30.
    K.N. Shirish, M. Dheevatsa, N. Jorge et al., On large-batch training for deep learning: Generalization gap and sharp minima, in International Conference on Learning Representations (2016). arXiv:1609.04836
  31. 31.
    L. Maaten, G. Hinton, Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008)zbMATHGoogle Scholar

Copyright information

© The Institution of Engineers (India) 2019

Authors and Affiliations

  1. 1.College of ScienceNortheast Agricultural UniversityHarbinChina
  2. 2.College of EngineeringNortheast Agricultural UniversityHarbinChina

Personalised recommendations