A CNN-Based Approach to Rice Plant Disease Classification: Overfitting Prevention Strategies
Article Sidebar
Main Article Content
Abstract
Rice plant diseases can be an interference to the production of cropping rice plants. The timely and precise detection and classification of the disease is the key to reduce the potential of deprived output. Convolutional Neural Networks (CNNs) have shown a great potential in image recognition and classification, including rice plant disease classification. Nevertheless, CNNs are likely to be overfitting. This research paper proposes a use of combination of overfitting prevention techniques for CNN-based approach to rice plant disease classification. The techniques used are data augmentation, max pooling with stride, dropout and early stopping. The CNN model with these overfitting avoidance strategies is trained to classify the disease of the rice plant leaves and resulted in a prediction accuracy of 0.93. We conclude that this CNN-based architecture is considered to be effective and reliable for rice plant disease classification.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Journal of TCI is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) licence, unless otherwise stated. Please read our Policies page for more information...
References
K. Ahmed, T. R. Shahidi, S. M. Irfanul Alam and S. Momen, “Rice Leaf Disease Detection Using Machine Learning Techniques,” In 2019 Proc. International Conference on Sustainable Technologies for Industry 4.0 (STI), Dhaka, Bangladesh, 2019, pp. 1-5,
doi: 10.1109/STI47673.2019.9068096.
T. Gayathri Devi and P. Neelamegam, “Image processing based rice plant leaves diseases in
Thanjavur, Tamilnadu”, Journal of Networks, Software Tools and Applications, vol. 22, Nov., pp. 13415–13428, 2019.
EL Mique Jr, TD Palaoag, “ Rice Pest and Disease Detection Using Convolutional Neural Network,” In 2018 Proc. International Conference on Information Science and System’04, 2018, pp. 147–151.
doi.org/10.1145/3209914.3209945.
R. Wang, “Mechanism and Design of Agriculture Pest and Disease Recognition System Based on Convolutional Neural Network,” In 2024 Proc. IEEE Eurasian Conference on Educational Innovation’07, 2024, pp. 291-295,
doi: 10.1109/ECEI60433.2024.10510856.
P. K. Kosamkar, V. Y. Kulkarni, K. Mantri, S. Rudrawar, S. Salmpuria and N. Gadekar, “Leaf disease detection and recommendation of pesticides using convolution neural network,” In Proc. International Conference on Computing Communication Control and Automation, 2019, pp. 1-4, doi: 10.1109/ECEI60433.2024.10510856.
K. O'shea and R. Nash, “An introduction to convolutional neural networks,” Current Issues in Neural and Evolutionary Computing, Dec, 2015. [Online serial].doi.org/10.48550/arXiv.1511.08458.
C. F. G. D. Santos and J. P. Papa, “ Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks,” Journal of Association for Computing Machinery, vol. 54, no. 10s, Sep, 2022. [Online serial]. doi.org/10.48550/arXiv.2201.03299.
P. Thanapol, K. Lavangnananda, P. Bouvry, F. Pinel and F. Leprévost, “Reducing overfitting and improving generalization in training convolutional neural network (CNN) under limited sample sizes in image recognition,” In Proc. International Conference on Information Technology’05, 2020, pp. 300-305, doi: 10.1109/InCIT50588.2020.9310787.
M. Vilares Ferro, Y. Doval Mosquera, F.J. Ribadas Pena et al., “ Early stopping by correlating online indicators in neural networks,” Neural Networks, Mar, 2022. [Online serial]. doi.org/10.1016/j.neunet.2022.11.035.
J. Dev, “Rice Plant diseases dataset,” kaggle.com, May, 2024. [Online]. Available: https://www.kaggle.com/code/jay7080dev/rice-plant-disease-detection. [Accessed May. 21, 2024].
R Riad, O Teboul, D Grangier, N Zeghidour, "Learning strides in convolutional neural networks," Current Issues in Machine Learning, pp. 1-17, Feb, 2022. [Online serial]. doi.org/10.48550/arXiv.2202.01653.
S. Cai, Y. Shu, G. Chen, B. C. Ooi, W. Wang and M. Zhang, “Effective and efficient dropout for deep convolutional neural networks,” https://arxiv.org/, Jul. 28, 2020. [Online]. doi.org/10.48550/arXiv.1904.03392.
A. Pauls and J. A. Yoder, "Determining optimum drop-out rate for neural networks," In 2018 Proc. International Conference on the Midwest Instruction and Computing Symposium, 2018, pp. 1-11.
A. Ravikumar, H. Sriraman, PM. Sai Saketh, S. Lokesh, and A. Karanam, “ Effect of neural network structure in accelerating performance and accuracy of a convolutional neural network with GPU/TPU for image analytics,” PeerJ Computer Science 8:e909, Mar, 2022. [Online serial]. doi.org/10.7717/peerj-cs.909.
D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” https://arxiv.org/, Jan. 30, 2017. [Online]. doi.org/10.48550/arXiv.1412.6980/.
J. T. S pringenberg, A. Dosovitskiy, T. Brox and M. Riedmiller, “Striving for simplicity: The all convolutional net,” https://arxiv.org/, Apr. 13, 2015. [Online]. doi.org/10.48550/arXiv.1412.6806/.