Rice Leaf Disease Classification Using Knowledge Distillation
Abstract
Rice is essential for global food security, particularly in Asian countries where it is a staple food and a
significant contributor to the economy. Rice cultivation faces numerous challenges, including a variety of illnesses that can significantly impact the yield and quality of the harvest. Conventional disease detection methods are slow, require a lot of manual effort, and are prone to mistakes, emphasizing the critical requirement for automated approaches. This research explores the implementation of knowledge distillation, a method of transferring expertise from advanced Models to more basic ones, for identifying diseases in rice. We condensed the expertise of complex Models by training them extensively, creating a streamlined and effective Model. We employed DenseNet121 as the Teacher Model, and the Student Model is equipped with dual pipeline Models to address overfitting. Both of these Models passed through Quantization Aware Training (QAT). The Student-Teacher collaborative Model achieved a precision of 98.47%, using significantly fewer parameters (5.9 million) than the Teacher-only Model. Finally, the whole Model was quantized to an 8-bit integer from 32-bit float points. This leads to a fairer method for effectively and accurately isolating small and complex characteristics. This small-scale is ideal for use on portable gadgets in environments with restricted resources, enabling farmers to quickly identify diseases for better crop management and increased worldwide food security measures.
References
S. Sen, R. Chakraborty, and P. Kalita, “Rice-not just a staple food: A comprehensive review on its phytochemicals and therapeutic potential,” Trends in Food Science & Technology, vol. 97, pp. 265–285, 2020.
“What is bangladesh? the kernel importance description,” of rice accessed: 03-17. [Online]. Available: https://typeset.io/questions/ what-is-the-importance-of-rice-in-bangladesh-4ibrf6r1us
R. Reinke, S. Kim, and B. Kim, “Developing japonica rice introgression lines with multiple resistance genes for
brown planthopper, bacterial blight, rice blast, and rice stripe virus using molecular breeding,” Molecular Genetics and Genomics, vol. 293, no. 6, pp. 1565–1575, 2018.
M. Agrawal and S. Agrawal, “Rice plant diseases detection & classification using deep learning models: A systematic review,” Journal of Critical Reviews, vol. 7, no. 11, pp. 4376–4390, 2020.
J. Chen, D. Zhang, Y. Nanehkaran, and D. Li, “Detection of rice plant diseases based on deep transfer learning,” Journal of the Science of Food and Agriculture, vol. 100, no. 7, pp. 3246–3256, 2020.
S. Jadhav, V. Udupi, and S. Patil, “Identification of plant diseases using convolutional neural networks,” International Journal of Information Technology, vol. 13, no. 6, pp. 24612470, 2021.
T. Daniya and S. Vigneshwari, “Deep neural network for disease detection in rice plant using the texture and deep features,” The Computer Journal, vol. 65, no. 7, pp. 1812 1825, 2022.
J. Li, X. Zhao, H. Xu, L. Zhang, B. Xie, J. Yan, L. Zhang, D. Fan, and L. Li, “An interpretable high-accuracy method
for rice disease detection based on multisource data and transfer learning,” Plants, vol. 12, no. 18, p. 3273, 2023.
A. Sharma, A. Jain, P. Gupta, and V. Chowdary, “Machine learning applications for precision agriculture: A comprehensive review,” IEEE Access, vol. 9, pp. 4843–4873, 2020.
G. Hinton, O. Vinyals, and J. Dean, “Distilling the knowledge in a neural network,” 2015. [Online]. Available:
https://arxiv.org/abs/1503.02531
A. Musa, M. Hassan, M. Hamada, and F. Aliyu, “Low power deep learning model for plant disease detection for smart-hydroponics using knowledge distillation techniques,” Journal of Low Power Electronics and Applications, vol. 12, no. 2, p. 24, 2022.
Y. Hu, G. Liu, Z. Chen, J. Liu, and J. Guo, “Lightweight one-stage maize leaf disease detection model with knowledge distillation,” Agriculture, vol. 13, no. 9, p. 1664, 2023.
B. Petchiammal, Kiruba and P. Murugan, Arjunan, “Paddy doctor: A visual image dataset for automated paddy disease classification and benchmarking,” in CODS-COMAD ’23. Association for Computing Machinery, New York, NY, USA, 2023, pp. 203–207.
S. Lamba, A. Baliyan, and V. Kukreja, “A novel gcl hybrid classification model for paddy diseases,” International Journal of Information Technology, 2022.
W. Chen, J. Chen, R. Duan, Y. Fang, Q. Ruan, and D. Zhang, “Ms-dnet: A mobile neural network for
plant disease identification,” Computers and Electronics in Agriculture, vol. 199, p. 107175, 2022. [Online].
Available: https://www.sciencedirect.com/science/article/pii/ S0168169922004926
S. Nalini, N. Krishnaraj, J. Thangaiyan, K. Vinothkumar, A. Britto, K. Subramaniam, and C. Bharatiraja, “Paddy leaf disease detection using an optimized deep neural network,” Computers, Materials & Continua, vol. 680, pp. 1117–1128, 2021.
M. Niaz, L. Tarin, T. Shabonty, M. Saad, and D. Farid, “Paddy leaf disease detection employing transfer learning,” in 2023 26th International Conference on Computer and Information Technology (ICCIT), 2023, pp. 1–6. in 2024
C. Simhadri and H. Kondaveeti, “Automatic recognition of rice leaf diseases using transfer learning,” Agronomy, vol. 13, no. 4, 2023. [Online]. Available: https://www.mdpi. com/2073-4395/13/4/961
R. Narmadha, N. Sengottaiyan, and R.J.K., “Deep transfer learning based rice plant disease detection model,” Intelligent Automation & Soft Computing, vol. 31, no. 2, pp. 1257–1271, 2022. [Online]. Available: http://www. techscience.com/iasc/v31n2/44553
V. Gautam, N. Trivedi, A. Singh, H. Mohamed, I. Noya, P. Kaur, and N. Goyal, “A transfer learning-based
artificial intelligence model for leaf disease assessment,” Sustainability, vol. 14, no. 20, 2022. [Online]. Available:
https://www.mdpi.com/2071-1050/14/20/13610
M. Islam, M. Shuvo, M. Shamsojjaman, S. Hasan, M. Hossain, and T. Khatun, “An automated convolutional neural network based approach for paddy leaf disease detection,” International Journal of Advanced Computer Science and Applications, vol. 12, no. 1, 2021.
A. Ghofrani and R. Mahdian Toroghi, “Knowledge distillation in plant disease recognition,” Neural Computing and Applications, vol. 34, no. 17, pp. 14287–14296, 2022. [Online]. Available: https: //doi.org/10.1007/s00521-021-06882-y
Y. Hu, G. Liu, Z. Chen, J. Liu, and J. Guo, “Lightweight one-stage maize leaf disease detection model with knowledge distillation,” Agriculture, vol. 13, no. 9, 2023. [Online]. Available: https://www.mdpi.com/2077-0472/13/9/1664
A. Musa, M. Hassan, M. Hamada, and F. Aliyu, “Low power deep learning model for plant disease detection for smart-hydroponics using knowledge distillation techniques,” Journal of Low Power Electronics and Applications, vol. 12, no. 2, 2022. [Online]. Available: https://www.mdpi.com/ 2079-9268/12/2/24
“Rice leaf disease detection obj dataset,” visited on 2024 03-18. [Online]. Available: https://universe.roboflow.com/ project-khcjh/rice-leaf-disease-detection-obj
“Rice leaf diseases dataset kernel description,” accessed: 2023-08-14. [Online]. Available: https://www.kaggle.com/datasets/vbookshelf/rice-leaf-diseases
“Rice diseases image dataset,” accessed: 2023-08.14. [Online]. Available: https://www.kaggle.com/datasets/
minhhuy2810/rice-diseases-imagedataset/data
