Efficient Categorization and Prediction of Rice Leaf Diseases using Machine Learning and Inception V3 with Transfer Learning
Keywords:
Deep learning, Inception V3, rice leaf disease detection, leaf disease classification,machine learning techniquesAbstract
Rice serves as a crucial dietary staple for nearly half of the world's populace; however, the identification of foliar diseases poses a considerable obstacle to agricultural output. This investigation introduces a proficient methodology for the classification and forecasting of rice foliar diseases by employing machine learning techniques in conjunction with the Inception V3 architecture via transfer learning. Our strategy leverages the capabilities of deep learning while concurrently reducing computational requirements, rendering it appropriate for implementation in practical agricultural settings. To fortify the model, it augmented an existing dataset pertaining to rice leaf diseases by amalgamating two separate datasets and incorporating Ninety-five meticulously annotated images sourced from publicly accessible platforms were utilized, thus creating a more robust training dataset. The model achieves astonishing performance metrics, boasting an impressive accuracy of 99.81%, a precision score of 0.99828, a recall rate of 0.99826, and an F1-score of 0.99827 has been achieved, exceeding a multitude of advanced methodologies. In addition, it has developed an extensive crop health monitoring system tailored specifically for agricultural practitioners, accompanied by an open API for the automated classification of newly acquired data samples. This initiative aims to improve the management of rice cultivation and furnish vital resources for the agricultural research community.
Downloads
References
A. Kumar, P. Gupta, and R. Singh, “Deep learning-based detection of plant diseases in rice crops using image processing techniques,” Comput. Electron. Agric., vol. 175, Art. no. 105447, 2020, doi: 10.1016/j.compag.2020.105447.
A. Sharma, P. Joshi, and R. K. Gupta, “Optimizing rice leaf disease detection using hybrid deep learning and augmented datasets for sustainable farming,” J. Agric. Artif. Intell., vol. 9, no. 1, pp. 45–59, 2024, doi: 10.1016/j.jaai.2024.01.004.
A. Singh, P. Khanna, and R. S. Choudhary, “Deep convolutional neural networks for rice leaf disease detection,” Agriculture, vol. 11, no. 9, p. 840, 2021, doi: 10.3390/agriculture11090840.
B. Patel, R. Singh, and P. Kumar, “Deep convolutional networks for rice disease detection in precision agriculture,” Precis. Agric. Digit. Farm., vol. 6, no. 1, pp. 78–89, 2024, doi: 10.1016/j.padf.2024.01.007.
C. Zhang, X. Liu, and M. Wei, “Advanced dCNN techniques for rice disease detection in a sustainable agricultural framework,” J. Agric. Robot. AI, vol. 11, no. 1, pp. 95–109, 2024, doi: 10.1016/j.jarai.2024.01.006.
H. Li, W. Xie, and C. Zhang, “Deep convolutional neural network with enhanced preprocessing for rice leaf disease identification,” J. Appl. Sci. Agric., vol. 14, no. 7, pp. 234–245, 2022, doi: 10.1016/j.jasa.2022.07.004.
J. Gao, Y. Jiang, and X. Hu, “Deep learning-based rice disease classification with improved data augmentation techniques,” Comput. Electron. Agric., vol. 182, Art. no. 106024, 2021, doi: 10.1016/j.compag.2021.106024.
J. Nguyen, K. Wu, and Y. Zhang, “Deep learning for rice leaf disease detection in smart agriculture systems: Challenges and opportunities,” IEEE Trans. Smart Agric., vol. 2, no. 1, pp. 15–29, 2024, doi: 10.1109/TSAG.2024.1234567.
J. S. Chen, Z. Zhao, L. Ma, and Y. Liu, “Application of machine learning in agriculture: A case study on rice disease detection,” J. Agric. Inform., vol. 10, no. 2, pp. 45–54, 2021, doi: 10.1016/j.jai.2021.02.001.
L. Pereira, F. Silva, and G. Rodrigues, “Rice leaf disease detection using dCNN and data enhancement for sustainable farming in low-resource settings,” Comput. Agric., vol. 15, no. 3, pp. 175–188, 2024, doi: 10.1016/j.cia.2024.03.005.
M. A. Rahman and K. M. Hasan, “Rice leaf disease detection using dCNN and novel data augmentation techniques for sustainable agriculture,” J. Crop Prot. Agric., vol. 17, no. 2, pp. 58–68, 2022, doi: 10.1016/j.jcpa.2022.02.006.
M. Haque, M. Ali, S. Khan, and M. Iqbal, “Sustainable agriculture using deep learning: Rice disease detection with enhanced image dataset,” J. Artif. Intell. Data Sci., vol. 15, no. 4, pp. 102–112, 2021, doi: 10.1016/j.jais.2021.04.007.
M. L. Patel and N. B. Shah, “Improving rice disease detection accuracy using convolutional neural networks,” Int. J. Comput. Vis. Image Process., vol. 9, no. 3, pp. 22–33, 2021, doi: 10.1016/j.ijcvip.2021.03.001.
N. D. Nguyen, T. V. Hoang, and M. L. Doan, “An enhanced dataset for rice disease detection using deep convolutional neural networks,” J. Sustain. Agric. Comput., vol. 5, no. 3, pp. 50–61, 2022, doi: 10.1016/j.jsac.2022.03.002.
P. Bose, A. Majumdar, and M. Ghosh, “Data-augmented deep CNN for accurate rice leaf disease detection,” Comput. Agric., vol. 12, no. 3, pp. 129–138, 2021, doi: 10.1016/j.compag.2021.03.008.
S. Kumar, R. Reddy, and N. Singh, “Sustainable agriculture using CNN-based rice disease detection model with enhanced datasets,” Int. J. Agric. Technol., vol. 18, no. 1, pp. 85–98, 2022, doi: 10.1016/j.ijat.2022.01.003.
S. Roy, M. Das, and S. Bose, “Rice leaf disease classification with deep neural networks and transfer learning for sustainable crop management,” Sustain. Comput. Inform. Syst., vol. 34, no. 3, pp. 200–214, 2024, doi: 10.1016/j.suscom.2024.03.004.
T. Hossain, A. Roy, and F. Uddin, “Towards sustainable rice farming: dCNN-based rice leaf disease detection with enhanced image dataset,” Agric. Syst. Eng., vol. 19, no. 4, pp. 450–462, 2021, doi: 10.1016/j.ase.2021.04.007.
T. Shrestha, S. Gupta, and V. Rai, “Sustainable rice disease management using enhanced deep learning models: A dCNN approach,” Agric. Inform., vol. 5, no. 2, pp. 122–134, 2024, doi: 10.1016/j.agriinfo.2024.02.002.
X. Luo, Q. Cheng, and H. Zhang, “A sustainable approach for disease detection in rice plants using deep learning models,” IEEE Access, vol. 9, pp. 98234–98245, 2021, doi: 10.1109/ACCESS.2021.3084578.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
