The Plant Pathology Journal

The Korean Society of Plant Pathology (한국식물병리학회)
권호 표지
DOI QR코드

DOI QR Code

An Analysis of Plant Diseases Identification Based on Deep Learning Methods

  • Xulu Gong (College of Agricultural Engineering, Shanxi Agricultural University) ;
  • Shujuan Zhang (College of Agricultural Engineering, Shanxi Agricultural University)
  • Received : 2023.03.02
  • Accepted : 2023.06.12
  • Published : 2023.08.01
Download PDF
⟨ Previous Next ⟩

Abstract

Plant disease is an important factor affecting crop yield. With various types and complex conditions, plant diseases cause serious economic losses, as well as modern agriculture constraints. Hence, rapid, accurate, and early identification of crop diseases is of great significance. Recent developments in deep learning, especially convolutional neural network (CNN), have shown impressive performance in plant disease classification. However, most of the existing datasets for plant disease classification are a single background environment rather than a real field environment. In addition, the classification can only obtain the category of a single disease and fail to obtain the location of multiple different diseases, which limits the practical application. Therefore, the object detection method based on CNN can overcome these shortcomings and has broad application prospects. In this study, an annotated apple leaf disease dataset in a real field environment was first constructed to compensate for the lack of existing datasets. Moreover, the Faster R-CNN and YOLOv3 architectures were trained to detect apple leaf diseases in our dataset. Finally, comparative experiments were conducted and a variety of evaluation indicators were analyzed. The experimental results demonstrate that deep learning algorithms represented by YOLOv3 and Faster R-CNN are feasible for plant disease detection and have their own strong points and weaknesses.

Keywords

Acknowledgement

This study was supported by the National Natural Science Foundation of China (No. 12202253), the Youth Science and Technology Innovation Project of Shanxi Agricultural University Grant (No. 2019019) and the Shanxi Provincial Key Research and Development Project (No. 201903D221027).

References

  1. AI Studio. 2019. Pathological image of apple leaf. URL https://aistudio.baidu.com/aistudio/datasetdetail/11591 [26 April 2023].
  2. Alemu, K. 2014. Real-time PCR and its application in plant disease diagnostics. Adv. Life Sci. Technol. 27:39-49.
  3. Alruwaili, M., Siddiqi, M. H., Khan, A., Azad, M., Khan, A. and Alanazi, S. 2022. RTF-RCNN: an architecture for real-time tomato plant leaf diseases detection in video streaming using Faster-RCNN. Bioengineering 9:565.
  4. Bhat, I. A., Bhat, R. A., Shrivastava, M. and Sharma, D. M. 2018. Universal dependency parsing for Hindi-English code-switching. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vol. 1, eds. by M. Walkter, H. Ji and A. Stent, pp. 987-998. Association for Computational Linguistics, New Orleans, LA, USA.
  5. Bhujel, A., Kim, N.-E., Arulmozhi, E., Basak, J. K. and Kim, H.-T. 2022. A lightweight attention-based convolutional neural networks for tomato leaf disease classification. Agriculture 12:228.
  6. Caldeira, R. F., Santiago, W. E. and Teruel, B. 2021. Identification of cotton leaf lesions using deep learning techniques. Sensors (Basel) 21:3169.
  7. Chang, Y. K., Zaman, Q. U., Schumann, A. W., Percival, D. C., Esau, T. J. and Ayalew, G. 2012. Development of color co-occurrence matrix based machine vision algorithms for wild blueberry fields. Appl. Eng. Agric. 28:315-323. https://doi.org/10.13031/2013.42321
  8. Chen, K., Wang, J., Pang, J., Cao, Y., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Xu, J., Zhang, Z., Cheng, D., Zhu, C., Cheng, T., Zhao, Q., Li, B., Lu, X., Zhu, R., Wu, Y., Dai, J., Wang, J., Shi, J., Ouyang, W., Loy, C. C. and Lin, D. 2019. MMDetection: open MMLab detection toolbox and benchmark. Preprint at https://doi.org/10.48550/arXiv.1906.07155.
  9. Cynthia, S. T., Hossain, K. M. S., Hasan, M. N., Asaduzzaman, M. and Das, A. K. 2019. Automated detection of plant diseases using image processing and Faster R-CNN algorithm. In: 2019 International Conference on Sustainable Technologies for Industry 4.0 (STI), pp. 1-5. Institute of Electrical and Electronics Engineers, Piscataway, NJ, USA.
  10. Dai, J., Li, Y., He, K. and Sun, J. 2016. R-FCN: object detection via region-based fully convolutional networks. In: Proceedings of the 30th International Conference on Neural Information Processing Systems, eds. by D. D. Lee, M. Sugiyama, U. Luxburg, I. Guyon and R. Garnett, pp. 379-387. Curran Associates Inc., Red Hook, NY, USA.
  11. Deng, R., Tao, M., Xing, H., Yang, X., Liu, C., Liao, K. and Qi, L. 2021. Automatic diagnosis of rice diseases using deep learning. Front. Plant Sci. 12:701038.
  12. Dubey, S. R. and Jalal, A. S. 2012. Detection and classification of apple fruit diseases using complete local binary patterns. In: 2012 Third International Conference on Computer and Communication Technology, pp. 346-351. IEEE Computer Society, Washington, DC, USA.
  13. Fernandez-Campos, M., Huang, Y. T., Jahanshahi, M. R., Wang, T., Jin, J., Telenko, D. E. P., Gongora-Canul, C. and Cruz, C. D. 2021. Wheat spike blast image classification using deep convolutional neural networks. Front. Plant Sci. 12:673505.
  14. Food and Agriculture Organization of the United Nations. 2021. Climate change fans spread of pests and threatens plants and crops, new FAO study. URL https://www.fao.org/newsroom/detail/Climate-change-fans-spread-of-pests-and-threatens-plants-and-crops-new-FAO-study/zh [26 April 2023].
  15. Girshick, R. 2015. Fast R-CNN. In: Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1440-1448. IEEE Computer Society, Washington, DC, USA.
  16. Girshick, R., Donahue, J., Darrell, T. and Malik, J. 2014. Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 580-587. IEEE Computer Society, Washington, DC, USA.
  17. He, K., Gkioxari, G., Dollar, P. and Girshick, R. 2017. Mask R-CNN. In: Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2980-2988. IEEE Computer Society, Washington, DC, USA.
  18. He, K., Zhang, X., Ren, S. and Sun, J. 2015. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37:1904-1916. https://doi.org/10.1109/TPAMI.2015.2389824
  19. He, K., Zhang, X., Ren, S. and Sun, J. 2016. Deep residual learning for image recognition. In: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770-778. IEEE Computer Society, Washington, DC, USA.
  20. Hlaing, C. S. and Maung Zaw, S. M. 2018. Tomato plant diseases classification using statistical texture feature and color feature. In: Proceedings of the 2018 IEEE/ACIS 17th International Conference on Computer and Information Science (ICIS), pp. 439-444. IEEE Computer Society, Los Alamitos, CA, USA.
  21. Hou, J., Yang, C., He, Y. and Hou, B. 2023. Detecting diseases in apple tree leaves using FPN-ISResNet-Faster RCNN. Eur. J. Remote Sens. 56:2186955.
  22. Jia, Y., Zhang, Q., Zhang, W. and Wang, X. 2019. Community-GAN: community detection with generative adversarial nets. In: The Web Conference 2019, eds. by L. Liu and R. White, pp. 784-794. Association for Computing Machinery, New York, NY, USA.
  23. Jos, J. and Venkatesh, K. A. 2020. Pseudo color region features for plant disease detection. In: 2020 IEEE International Conference for Innovation in Technology (INOCON 2020), pp. 1-5. Institute of Electrical and Electronics Engineers, Piscataway, NJ, USA.
  24. Karadag, K., Tenekeci, M. E., Tasaltin, R. and Bilgili, A. 2020. Detection of pepper fusarium disease using machine learning algorithms based on spectral reflectance. Sustain. Comput. Inform. Syst. 28:100299.
  25. Krizhevsky, A., Sutskever, I. and Hinton, G. E. 2012. ImageNet classification with deep convolutional neural networks. Adv. Neural Inf. Process Syst. 25:1097-1105.
  26. Li, J.-H., Lin, L.-J. and Tian, K. 2020a. Detection of leaf diseases of balsam pear in the field based on improved Faster R-CNN. Trans. Chin. Soc. Agric. Eng. 36:179-185 (in Chinese).
  27. Li, Z., Guo, R., Li, M., Chen, Y. and Li, G. 2020b. A review of computer vision technologies for plant phenotyping. Comput. Electron. Agric. 176:105672.
  28. Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B. and Belongie, S. 2017. Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 936-944. Institute of Electrical and Electronics Engineers, Piscataway, NJ, USA.
  29. Liu, J. and Wang, X. 2020. Tomato diseases and pests detection based on improved Yolo V3 convolutional neural network. Front. Plant Sci. 11:898.
  30. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y. and Berg, A. C. 2016. SSD: single shot MultiBox detector. In: Computer Vision - ECCV 2016, eds. by B. Leibe, J. Matas, N. Sebe and M. Welling, pp. 21-37. Springer, Cham, Switzerland.
  31. Mathew, M. P. and Mahesh, T. Y. 2022. Leaf-based disease detection in bell pepper plant using YOLO v5. Signal Image Video Process. 16:841-847. https://doi.org/10.1007/s11760-021-02024-y
  32. Nandhini, N. and Bhavani, R. 2020. Feature extraction for diseased leaf image classification using machine learning. In: 2020 International Conference on Computer Communication and Informatics (ICCCI), pp. 1-4. Institute of Electrical and Electronics Engineers, Piscataway, NJ, USA.
  33. Nawaz, M., Nazir, T., Javed, A., Masood, M., Rashid, J., Kim, J. and Hussain, A. 2022. A robust deep learning approach for tomato plant leaf disease localization and classification. Sci. Rep. 12:18568.
  34. Pradhan, P., Kumar, B. and Mohan, S. 2022. Comparison of various deep convolutional neural network models to discriminate apple leaf diseases using transfer learning. J. Plant Dis. Protec. 129:1461-1473. https://doi.org/10.1007/s41348-022-00660-1
  35. Pushpa, B. R., Shree Hari, A. V. and Adarsh, A. 2021. Diseased leaf segmentation from complex background using indices based histogram, In: Computational and Experimental Simulations in Engineering: Proceedings of ICCES 2020. Vol. 1, eds. by S. N. Atluri and I. Vusanovic, pp. 1502-1507. Springer, Cham, Switzerland.
  36. Redmon, J., Divvala, S. K., Girshick, R. B. and Farhadi, A. 2016. You only look once: unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779-788. IEEE Computer Society, Washington, DC, USA.
  37. Redmon, J. and Farhadi, A. 2017. YOLO9000: better, faster, stronger. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6517-6525. IEEE Computer Society, Washington, DC, USA.
  38. Redmon, J. and Farhadi, A. 2018. YOLO V3: an incremental improvement. Preprint at https://doi.org/10.48550/arXiv.1804.02767.
  39. Ren, S., He, K., Girshick, R. and Sun, J. 2017. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39:1137-1149. https://doi.org/10.1109/TPAMI.2016.2577031
  40. Sardogan, M., Ozen, Y. and Tuncer, A. 2020. Detection of apple leaf diseases using Faster R-CNN. Duzce Univ. J. Sci. Technol. 8:1110-1117. https://doi.org/10.29130/dubited.648387
  41. Shrivastava, V. K. and Pradhan, M. K. 2021. Rice plant disease classification using color features: a machine learning paradigm. J. Plant Pathol. 103:17-26. https://doi.org/10.1007/s42161-020-00683-3
  42. Simon, M., Milz, S., Amende, K. and Gross, H.-M. 2019. Complex-YOLO: an Euler-Region-Proposal for real-time 3D object detection on point clouds. In: Computer Vision - ECCV 2018, eds. by L. Leal-Taixe and S. Roth, pp. 197-209. Springer, Cham, Switzerland.
  43. Simonyan, K. and Zisserman, A. 2015. Very deep convolutional networks for large-scale image recognition. Preprint at https://arxiv.org/abs/1409.1556.
  44. Srivastava, A., Jha, D., Chanda, S., Pal, U., Johansen, H. D., Johansen, D., Riegler, M. A., Ali, S. and Halvorsen, P. 2021. MSRF-Net: a multi-scale residual fusion network for biomedical image segmentation. IEEE J. Biomed. Health Inform. 26:2252-2263. https://doi.org/10.1109/JBHI.2021.3138024
  45. Sterling, A. and Melgarejo, L. M. 2020. Leaf spectral reflectance of Hevea brasiliensis in response to Pseudocercospora ulei. Eur. J. Plant Pathol. 156:1063-1076. https://doi.org/10.1007/s10658-020-01961-7
  46. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V. and Rabinovich, A. 2015. Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1-9. IEEE Computer Society, Washington, DC, USA.
  47. Tamuli, P. 2020. The polymerase chain reaction (PCR) and plant disease diagnosis: a review. Plant Arch. 20:3495-3498.
  48. Taohidul Islam, S. M., Masud, M. A., Ur Rahaman, M. A. and Hasan Rabbi, M. M. 2019. Plant leaf disease detection using mean value of pixels and canny edge detector. In: 2019 International Conference on Sustainable Technologies for Industry 4.0 (STI), pp. 1-6. Institute of Electrical and Electronics Engineers, Piscataway, NJ, USA.
  49. Thapa, R., Zhang, K., Snavely, N., Belongie, S. and Khan, A. 2020. The Plant Pathology Challenge 2020 data set to classify foliar disease of apples. Appl. Plant Sci. 8:e11390.
  50. Tian, Y., Yang, G., Wang, Z., Li, E. and Liang, Z. 2019. Detection of apple lesions in orchards based on deep learning methods of CycleGAN and YOLOV3-Dense. J. Sens. 2019:7630926.
  51. Tugrul, B., Elfatimi, E. and Eryigit, R. 2022. Convolutional neural networks in detection of plant leaf diseases: a review. Agriculture 12:1192.
  52. Waheed, A., Goyal, M., Gupta, D., Khanna, A., Hassanien, A. E. and Pandey, H. M. 2020. An optimized dense convolutional neural network model for disease recognition and classification in corn leaf. Comput. Electron. Agric. 175:105456.
  53. Wang, Q. and Qi, F. 2019. Tomato diseases recognition based on Faster RCNN. In: 2019 10th International Conference on Information Technology in Medicine and Education (ITME 2019), pp. 772-776. Institute of Electrical and Electronics Engineers, Piscataway, NJ, USA.
  54. Wang, X. and Liu, J. 2021. Tomato anomalies detection in greenhouse scenarios based on YOLO-Dense. Front. Plant Sci. 12:634103.
  55. Wang, Y., Wang, Y. and Zhao, J. 2022. MGA-YOLO: a lightweight one-stage network for apple leaf disease detection. Front. Plant Sci. 13:927424.
  56. Wani, J. A., Sharma, S., Muzamil, M., Ahmed, S., Sharma, S. and Singh, S. 2022. Machine learning and deep learning based computational techniques in automatic agricultural diseases detection: methodologies, applications, and challenges. Arch. Comput. Methods Eng. 29:641-677. https://doi.org/10.1007/s11831-021-09588-5
  57. Yan, Q., Yang, B., Wang, W., Wang, B., Chen, P. and Zhang, J. 2020. Apple leaf diseases recognition based on an improved convolutional neural network. Sensors (Basel) 20:3535.
  58. Zhang, K., Xu, Z., Dong, S., Cen, C. and Wu, Q. 2019. Identification of peach leaf disease infected by Xanthomonas campestris with deep learning. Eng. Agric. Environ. Food 12:388-396. https://doi.org/10.1016/j.eaef.2019.05.001
  59. Zhang, Y., Qin, J., Park, D. S., Han, W., Chiu, C.-C., Pang, R., Le, Q. V. and Wu, Y. 2020. Pushing the limits of semi-supervised learning for automatic speech recognition. Preprint at https://doi.org/10.48550/arXiv.2010.10504.
  60. Zhou, C., Zhou, S., Xing, J. and Song, J. 2021. Tomato leaf disease identification by restructured deep residual dense network. IEEE Access 9:28822-28831. https://doi.org/10.1109/ACCESS.2021.3058947