Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Identification of crop diseases using improved convolutional neural networks

© The Institution of Engineering and Technology
Received 20/02/2019, Accepted 31/05/2020, Revised 23/03/2020, Published 10/06/2020

Conventional AlexNet has the problems of slow training speed, single characteristic scale and low recognition accuracy. To solve these problems, a convolutional neural network identification model based on Inception module and dilated convolution is proposed in this study. The inception module combined with dilated convolution, could extract disease characteristics at different scales and increase the receptive field. By setting different parameters, six improved models were obtained. They were trained to identify 26 diseases of 14 different crops; then the authors selected optimal recognition model. On this basis, the segmented dataset and the grey-scaled dataset were trained as comparative experiments to explore the influence of background and colour features on the recognition results. After only two training epochs, the improved optimal model could achieve an accuracy of over 95%. Moreover, the final average identification accuracy reached 99.37%. Contrast experiments indicate that colour and background features may influence the recognition effect. The improved model can extract disease information from different scales in the feature map to identify diverse diseases of different crops. The proposed model has faster training speed and higher recognition accuracy than the traditional model, and thus it can provide a reference for crop disease identification in actual production.

Inspec keywords: image segmentation; crops; plant diseases; learning (artificial intelligence); convolutional neural nets; feature extraction; image recognition

Other keywords: background features; convolutional neural network identification model; crop disease identification; disease information; disease characteristics; grey-scaled dataset; improved convolutional neural networks; dilated convolution; training speed; improved model; segmented dataset; optimal recognition model; colour features; inception module; AlexNet; single characteristic scale; receptive field; training epochs

Subjects: Knowledge engineering techniques; Neural computing techniques; Image recognition; Agriculture, forestry and fisheries computing; Computer vision and image processing techniques; Agriculture

References

    1. 1)
      • 14. Lecun, Y., Boser, B., Denker, J.S., et al: ‘Backpropagation applied to handwritten zip code recognition’, Neural. Comput., 1989, 1, (4), pp. 541–551.
    2. 2)
      • 3. Tan, W., Zhao, C., Wu, H., et al: ‘Hierarchical pathology image recognition based on elastic momentum deep learning neural network’, Trans. Chi. Soc. Agric. Mach., 2015, 46, (1), pp. 20–25.
    3. 3)
      • 35. Szegedy, C., Ioffe, S., Vanhoucke, V., et al: ‘Inception-v4, inception-ResNet and the impact of residual connections on learning’, 2016.
    4. 4)
      • 24. Dyrmann, M., Karstoft, H., Midtiby, H.S.: ‘Plant species classification using deep convolutional neural network’, Biosyst. Eng., 2016, 151, pp. 72–80.
    5. 5)
      • 11. Bankar, S., Dube, A., Kadam, P., et al: ‘Plant disease detection techniques using canny edge detection & color histogram in image processing’, Int. J. Comput. Sci. Inf. Technol., 2014, 5, (2), pp. 1165–1168.
    6. 6)
      • 15. Gong, D., Cao, C.: ‘Plant leaf classification based on convolutional neural network’, Comput. Modernization, 2014, 2014, (4), pp. 12–15.
    7. 7)
      • 2. Liu, T., Zhong, X., Sun, C., et al: ‘Computer vision-based identification of rice leaf diseases’, Agric. Sci. China, 2014, 47, (4), pp. 664–674.
    8. 8)
      • 13. Fukushima, K.: ‘Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position’, Biol. Cybern., 1980, 36, (4), pp. 193–202.
    9. 9)
      • 37. He, K., Zhang, X., Ren, S., et al: ‘Identity mappings in deep residual networks’, 2016, pp. 1–15.
    10. 10)
      • 5. Srdjan, S., Marko, A., Andras, A., et al: ‘Deep neural networks based recognition of plant diseases by leaf image classification’, Comput. Intel. Neurosci., 2016, 2016, pp. 1–11.
    11. 11)
      • 12. Ma, Y., Wen, Y., Li, X., et al: ‘Diagnostic system of greenhouse cucumber downy mildew based on image processing’, Trans. Chin. Soc. Agric. Mach., 2017, 48, (2), pp. 195–202.
    12. 12)
      • 25. Lu, Y., Yi, S., Zeng, N., et al: ‘Identification of rice diseases using deep convolutional neural networks’, Neurocomputing, 2017, 267, pp. 378–384.
    13. 13)
      • 34. Szegedy, C., Vanhoucke, V., Ioffe, S., et al: ‘Rethinking the inception architecture for computer vision’. Computer Vision and Pattern Recognition, Las Vegas, Nevada, USA., June 2016, pp. 2818–2826.
    14. 14)
      • 26. Cheng, X., Zhang, Y., Chen, Y., et al: ‘Pest identification via deep residual learning in complex background’, Comput. Electron. Agric., 2017, 141, pp. 351–356.
    15. 15)
      • 39. Jayme, G.A.B.: ‘Plant disease identification from individual lesions and spots using deep learning’, Biosystems Eng., 2019, 180, pp. 97–107.
    16. 16)
      • 38. Girish, A., Priti, B.: ‘Potato leaf diseases detection and classification system’, Int. J. Comput. Sci. Mob. Comput., 2016, 2, pp. 76–88.
    17. 17)
      • 1. Zhang, Y., Gao, Y., Wang, X.: ‘Problems and countermeasures of crop pest control’, Agric. Technol., 2017, 37, (1), pp. 117–118.
    18. 18)
      • 30. Wan, L., Zeiler, M.D., Zhang, S., et al: ‘Regularization of neural networks using DropConnect’. Int. Conf. on Machine Learning, Atlanta, GA, USA., June 2013, pp. 1058–1066.
    19. 19)
      • 32. Lin, M., Chen, Q., Yan, S.: ‘Network in network’, Comput. Sci., arXiv: 1312.4400, 2013.
    20. 20)
      • 31. Srivastava, N., Hinton, G., Krizhevsky, A., et al: ‘Dropout: a simple way to prevent neural networks from overfitting’, J. Mach. Learn. Res., 2014, 15, (1), pp. 1929–1958.
    21. 21)
      • 23. Chen, L.C., Papandreou, G., Kokkinos, I., et al: ‘Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs’, IEEE Trans. Pattern Anal. Mach. Intell., 2018, 40, (4), pp. 834–848.
    22. 22)
      • 16. Zhang, S., Huai, Y.: ‘Research on plant leaf recognition based on layered convolution depth learning system’, J. Beijing Forestry Univ., 2016, 38, (9), pp. 108–115.
    23. 23)
      • 20. Sun, Y., Liang, D., Wang, X., et al: ‘DeepID3: face recognition with very deep neural networks’, Comput. Sci., arXiv: 1502.00873, 2015.
    24. 24)
      • 17. Zeiler, M.D., Fergus, R.: ‘Visualizing and understanding convolutional networks’, Dept. Comput. Sci., New York Univ., 2013, 8689, pp. 818–833.
    25. 25)
      • 33. Kudo, Y., Aoki, Y.: ‘Dilated convolutions for image classification and object localization’. Fifteenth Iapr Int. Conf. on Machine Vision Applications, Nagoya, Japan, May 2017, pp. 452–455.
    26. 26)
      • 27. Too, E.C., Yujian, L., Njuki, S., et al: ‘A comparative study of fine-tuning deep learning models for plant disease identification’, Comput. Electron. Agric., 2019, 161, pp. 272–279.
    27. 27)
      • 29. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ‘Imagenet classification with deep convolutional neural networks’. Int. Conf. on Neural Information Processing Systems, Curran Associates Inc., Lake Tahoe, Nevada, USA., December 2012, pp. 1097–1105.
    28. 28)
      • 22. Chen, L.C., Papandreou, G., Kokkinos, I., et al: ‘Semantic image segmentation with deep convolutional nets and fully connected CRFs’, Comput. Sci., 2014, 4, (4), pp. 357–361.
    29. 29)
      • 18. Goodfellow, I.J., Bulatov, Y., Ibarz, J., et al: ‘Multi-digit number recognition from street view imagery using deep convolutional neural networks’ arXiv: 1312. 6082, 2013.
    30. 30)
      • 7. Johannes, A., Picon, A., Alvarez-Gila, A., et al: ‘Automatic plant disease diagnosis using mobile capture devices, applied on a wheat use case’, Comput. Electron. Agric., 2017, 138, pp. 200–209.
    31. 31)
      • 19. Parkhi, O.M., Vedaldi, A., Zisserman, A.: ‘Deep face recognition’, British Mach. Vision Conf., 2015, 41, pp. 1–12.
    32. 32)
      • 10. Liu, P., Tu, K., Xu, H., et al: ‘Persimmon surface disease recognition based on support vector machine’, Modern Food Sci. Technol., 2011, 27, (3), pp. 349–353.
    33. 33)
      • 36. Ketkar, N.: ‘Stochastic gradient descent’, in Deep Learning with Python (Apress, Berkeley, CA, 2017), pp. 111–130.
    34. 34)
      • 9. Tellaeche, A., Burgosartizzu, X.P., Pajares, G., et al: ‘A vision-based method for weeds identification through the Bayesian decision theory’, Pattern. Recogn., 2008, 41, (2), pp. 521–530.
    35. 35)
      • 8. Ghazi, M.M., Yanikoglu, B., Aptoula, E.: ‘Plant identification using deep neural networks via optimization of transfer learning parameters’, Neurocomputing, 2017, 235, pp. 228–235.
    36. 36)
      • 28. Guan, T., Zhu, H.: ‘Atrous faster R-CNN for small scale object detection’. Int. Conf. on Multimedia and Image Processing, 2017, pp. 16–21.
    37. 37)
      • 4. Sun, J., Tan, W., Mao, H., et al: ‘Recognition of multiple plant leaf diseases based on improved convolutional neural network’, Trans. Chin. Soc. Agric. Eng., 2017, 33, (19), pp. 209–215.
    38. 38)
      • 6. Mohanty, S.P., Hughes, D.P., Salathé, M.: ‘Using deep learning for image-based plant disease detection’, Front. Plant. Sci., 2016, 7, p.1419.
    39. 39)
      • 21. Dai, J., Li, Y., He, K., et al: ‘R-FCN: object detection via region-based fully convolutional networks’. 30th Conf. on Neural Information Processing Systems (NIPS), Barcelona, Spain, 2016.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2019.0136
Loading

Related content

content/journals/10.1049/iet-cvi.2019.0136
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address