International Journal of Computer Science & Network Security

International Journal of Computer Science & Network Security (국제컴퓨터통신보호논문지학회)
권호 표지
DOI QR코드

DOI QR Code

Early Detection of Rice Leaf Blast Disease using Deep-Learning Techniques

  • Syed Rehan Shah (Muhammad Nawaz Shareef University of Agriculture Multan) ;
  • Syed Muhammad Waqas Shah (Department of Computer Science,National University of Modern Languages) ;
  • Hadia Bibi (Department of Computer Science, BZU Multan) ;
  • Mirza Murad Baig (Department of Computer Science,National University of Modern Languages)
  • Received : 2024.04.05
  • Published : 2024.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

Pakistan is a top producer and exporter of high-quality rice, but traditional methods are still being used for detecting rice diseases. This research project developed an automated rice blast disease diagnosis technique based on deep learning, image processing, and transfer learning with pre-trained models such as Inception V3, VGG16, VGG19, and ResNet50. The modified connection skipping ResNet 50 had the highest accuracy of 99.16%, while the other models achieved 98.16%, 98.47%, and 98.56%, respectively. In addition, CNN and an ensemble model K-nearest neighbor were explored for disease prediction, and the study demonstrated superior performance and disease prediction using recommended web-app approaches.

Keywords

References

  1. S. U. Siddiqui, T. Kumamaru, and H. Satoh, "Pakistan rice genetic resources-I: Grain morphological diversity and its distribution," Pakistan Journal of Botany, vol. 39, no. 3, pp. 841-848, 2007.
  2. H.-u. Rehman, T. Aziz, M. Farooq, A. Wakeel, and Z. Rengel, "Zinc nutrition in rice production systems: a review," Plant Soil Biology and Biochemistry, vol. 361, no. 1, pp. 203-226, 2012.
  3. B. S. Chauhan, K. Jabran, and G. Mahajan, Rice production worldwide. Springer, 2017.
  4. M. Shahbandeh. (2022, 12). Top countries based on the production of milled rice 2020/21. Available: https://www.statista.com/statistics/255945/topcountries-of-destination-for-us-rice-exports-2011/
  5. OEC. (2020, 05). Rice In Pakistan. Available: https://oec.world/en/profile/bilateralproduct/rice/reporter/pak
  6. A. Rehman, L. Jingdong, A. A. Chandio, M. Shabbir, and I. Hussain, "Economic outlook of rice crops in Pakistan: a time series analysis (1970-2015)," Financial innovation, vol. 3, no. 1, pp. 1-9, 2017. https://doi.org/10.1186/s40854-016-0051-8
  7. T. Uzzaman, R. Sikder, M. Asif, H. Mehraj, and A. J. Uddin, "Growth and yield trial of sixteen rice varieties under System of Rice Intensification," Sci Agric, vol. 11, no. 2, pp. 81-89, 2015.
  8. C. R. Rahman et al., "Identification and recognition of rice diseases and pests using convolutional neural networks," Biosystems Engineering, vol. 194, pp. 112-120, 2020. https://doi.org/10.1016/j.biosystemseng.2020.03.020
  9. A. Kaur, K. Guleria, and N. K. Trivedi, "Rice Leaf Disease Detection: A Review," in 2021 6th International Conference on Signal Processing, Computing and Control (ISPCC), 2021, pp. 418-422: IEEE.
  10. H. B. Prajapati, J. P. Shah, and V. K. Dabhi, "Detection and classification of rice plant diseases," Intelligent Decision Technologies, vol. 11, no. 3, pp. 357-373, 2017. https://doi.org/10.3233/IDT-170301
  11. L. Nalley, F. Tsiboe, A. Durand-Morat, A. Shew, and G. Thoma, "Economic and environmental impact of rice blast pathogen (Magnaporthe oryzae) alleviation in the United States," PloS one, vol. 11, no. 12, p. e0167295, 2016.
  12. C. Duku, A. H. Sparks, and S. J. Zwart, "Spatial modeling of rice yield losses in Tanzania due to bacterial leaf blight and leaf blast in a changing climate," Climatic change, vol. 135, no. 3, pp. 569-583, 2016. https://doi.org/10.1007/s10584-015-1580-2
  13. C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, "Rethinking the inception architecture for computer vision," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 2818-2826.
  14. B. Kien et al., "Crack detection of plastic gears using a convolutional neural network pre-learned from images of meshing vibration data with transfer learning," Forschung in Ingenieurwesen, vol. 83, no. 3, pp. 645-653, 2019. https://doi.org/10.1007/s10010-019-00354-5
  15. M. Abdullah, S. Ghazanfar, J. Ahmed, and I. Khan, "Growth and instability analysis of rice production and export of Pakistan," European Journal of Economic Studies, no. 1, pp. 4-15, 2015.
  16. S. Kouser and K. Mushtaq, "Environmental efficiency analysis of basmati rice production in Punjab, Pakistan: Implications for sustainable agricultural development," The Pakistan Development Review, pp. 57-72, 2010.
  17. K. Ahmed, T. R. Shahidi, S. M. I. Alam, and S. Momen, "Rice leaf disease detection using machine learning techniques," in 2019 International Conference on Sustainable Technologies for Industry 4.0 (STI), 2019, pp. 1-5: IEEE.
  18. Y. Lu, S. Yi, N. Zeng, Y. Liu, and Y. Zhang, "Identification of rice diseases using deep convolutional neural networks," Neurocomputing, vol. 267, pp. 378-384, 2017. https://doi.org/10.1016/j.neucom.2017.06.023
  19. W.-j. Liang, H. Zhang, G.-f. Zhang, and H.-x. Cao, "Rice blast disease recognition using a deep convolutional neural network," Scientific reports of cetacean research, vol. 9, no. 1, pp. 1-10, 2019. https://doi.org/10.1038/s41598-018-37186-2
  20. S. Qadri et al., "Machine Vision Approach for Classification of Rice Varieties Using Texture Features," International Journal of Food Properties, vol. 24, no. 1, pp. 1615-1630, 2021. https://doi.org/10.1080/10942912.2021.1986523
  21. M. S. Irshad, Q. Xin, and H. Arshad, "Competitiveness of Pakistani rice in international market and export potential with the global world: A panel gravity approach," Cogent Economics Finance, vol. 6, no. 1, p. 1486690, 2018.
  22. J. Chen, D. Zhang, Y. A. Nanehkaran, and D. Li, "Detection of rice plant diseases based on deep transfer learning," Journal of the Science of Food Agriculture, vol. 100, no. 7, pp. 3246-3256, 2020. https://doi.org/10.1002/jsfa.10365
  23. J. Q. Yuan, L. Li, and W. Yan, "Early Identification of Rice Leaf Blast Based on Hyperspectral Imaging," in Journal of Physics: Conference Series, 2021, vol. 1944, no. 1, p. 012041: IOP Publishing.
  24. K. Kiratiratanapruk, P. Temniranrat, A. Kitvimonrat, W. Sinthupinyo, and S. Patarapuwadol, "Using deep learning techniques to detect rice diseases from images of rice fields," in International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, 2020, pp. 225-237: Springer.
  25. P. K. Sethy, N. K. Barpanda, A. K. Rath, and S. K. Behera, "Deep feature based rice leaf disease identification using support vector machine," Computers Electronics in Agriculture, vol. 175, p. 105527, 2020.
  26. G. Zhou, W. Zhang, A. Chen, M. He, and X. Ma, "Rapid detection of rice disease based on FCM-KM and faster R-CNN fusion," IEEE Access, vol. 7, pp. 143190-143206, 2019. https://doi.org/10.1109/ACCESS.2019.2943454
  27. H. Yang, J. Ni, J. Gao, Z. Han, and T. Luan, "A novel method for peanut variety identification and classification by Improved VGG16," Scientific Reports vol. 11, no. 1, pp. 1-17, 2021.
  28. M. Uzair, S. S. Sohail, N. U. Shaikh, and A. Shan, "Agricultural residue as an alternate energy source: A case study of Punjab province, Pakistan," Renewable Energy, vol. 162, pp. 2066-2074, 2020. https://doi.org/10.1016/j.renene.2020.10.041
  29. S. Frolking et al., "Combining remote sensing and ground census data to develop new maps of the distribution of rice agriculture in China," Global Biogeochemical Cycles, vol. 16, no. 4, pp. 38-1-38- 10, 2002.
  30. D. Mohapatra, J. Tripathy, and T. K. Patra, "Rice disease detection and monitoring using CNN and Naive Bayes classification," in Soft Computing Techniques and Applications: Springer, 2021, pp. 11-29.
  31. A. A. Joshi and B. Jadhav, "Monitoring and controlling rice diseases using Image processing techniques," in 2016 International Conference on Computing, Analytics and Security Trends (CAST), 2016, pp. 471-476: IEEE.
  32. A. I. Khan and S. Al-Habsi, "Machine learning in computer vision," Procedia Computer Science, vol. 167, pp. 1444-1451, 2020. https://doi.org/10.1016/j.procs.2020.03.355
  33. M. H. Masood, H. Saim, M. Taj, and M. M. Awais, "Early disease diagnosis for rice crop," arXiv preprint 2020.
  34. K. Bashir, M. Rehman, and M. Bari, "Detection and classification of rice diseases: An automated approach using textural features," Mehran University Research Journal of Engineering Technology, vol. 38, no. 1, pp. 239-250, 2019. https://doi.org/10.22581/muet1982.1901.20
  35. M. R. Larijani, E. A. Asli-Ardeh, E. Kozegar, and R. Loni, "Evaluation of image processing technique in identifying rice blast disease in field conditions based on KNN algorithm improvement by K-means," Food science nutrition, vol. 7, no. 12, pp. 3922-3930, 2019.
  36. Z. Jiang, Z. Dong, W. Jiang, and Y. Yang, "Recognition of rice leaf diseases and wheat leaf diseases based on multi-task deep transfer learning," Computers Electronics in Agriculture, vol. 186, p. 106184, 2021.
  37. Shareef. (2021, 4 Jun). Rice Leaf Disease Dataset Available: https://www.kaggle.com/code/asheniranga/notebook7fe71548bd
  38. S. A. Shahriar, A. A. Imtiaz, M. B. Hossain, A. Husna, and M. N. K. Eaty, "Rice blast disease," Annual Research Review in Biolog, pp. 50-64, 2020.
  39. J. Chen, D. Zhang, Y. A. Nanehkaran, and D. Li, "Detection of rice plant diseases based on deep transfer learning," Journal of the Science of Food Agriculture, vol. 100, no. 7, pp. 3246-3256, 2020. https://doi.org/10.1002/jsfa.10365
  40. H. D. Prasetyo, H. Triatmoko, and I. N. Isnainiyah, "The Implementation of CNN on Website-based Rice Plant Disease Detection," in 2020 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS), 2020, pp. 75-80: IEEE.