OPTIMIZATION OF TOMATO LEAF DISEASE DETECTION USING DEEP MACHINE LEARNING WITH ADVANCED NEURAL NETWORKS

Roman Humeniuk; Yulian Fedirko

The article discusses the application of deep machine learning methods for detecting tomato leaf diseases. The goal of the study is to improve the accuracy of classifying images of diseased plants through modifications to convolutional neural networks (CNN), combining the Inception module, the Mish activation function, and batch normalization. The proposed approach outperforms basic CNN models and the support vector machine method. The PlantVillage dataset, containing images of both diseased and healthy plants, was used for model evaluation. The results showed that the InceptionV3 network with the proposed module achieved the highest accuracy (97.8%) and demonstrated high efficiency for viral tomato diseases. The originality of the work lies in the development of a new module that significantly improves model performance. The practical value of the study is in applying these methods to mobile applications, enabling early detection of plant diseases. Further research will focus on expanding the module’s application to other plant diseases and optimizing it for real-world use.

convolutional neural network; leaf disease classification; Mish activation function; optimization; PlantVillage dataset; support vector machine; Inception module

[1] M. Van Dijk, T. Morley, M. L. Rau, and Y. Saghai, "A meta-analysis of projected global food demand and population at risk of hunger for the period 2010–2050," Nat. Food, vol. 2, pp. 494–501, 2021. https://doi.org/10.1038/s43016-021-00322-9

[2] G. Ghisbain, M. Gérard, T. J. Wood, H. M. Hines, and D. Michez, "Expanding insect pollinators in the Anthropocene," Biol. Rev., vol. 96, pp. 2755–2770, 2021. https://doi.org/10.1111/brv.12777

[3] C. Ferracini, V. H. P. Bueno, M. L. Dindo, B. L. Ingegno, M. G. Luna, N. G. Salas Gervassio, N. E. Sánchez, G. Siscaro, J. C. van Lenteren, L. Zappalà, et al., "Natural enemies of Tuta absoluta in the Mediterranean Basin, Europe and South America," Biocontrol Sci. Technol., vol. 29, pp. 578–609, 2019. https://doi.org/10.1080/09583157.2019.1572711.

[4] W. Albattah, M. Nawaz, A. Javed, M. Masood, and S. Albahli, "A novel deep learning method for detection and classification of plant diseases," Complex Intell. Syst., vol. 8, pp. 507–524, 2022. https://doi.org/10.1007/s40747-021-00536-1.

[5] S. H. Lee, H. Goëau, P. Bonnet, and A. Joly, "New perspectives on plant disease characterization based on deep learning," Comput. Electron. Agric., vol. 170, 105220, 2020. https://doi.org/10.1016/j.compag.2020.105220.

[6] D. P. Hughes and M. Salathe, "An open access repository of images on plant health to enable the development of mobile disease diagnostics," arXiv, arXiv:1511.08060, 2015.

[7] A. Ramcharan, K. Baranowski, P. McCloskey, B. Ahmed, J. Legg, and D. P. Hughes, "Deep learning for image-based cassava disease detection," Front. Plant Sci., vol. 8, 1852, 2017. https://doi.org/10.3389/fpls.2017.01852.

[8] J. Lu, L. Tan, and H. Jiang, "Review on convolutional neural network (CNN) applied to plant leaf disease classification," Agriculture, vol. 11, 707, 2021. https://doi.org/10.3390/agriculture11080707.

[9] A. Guerrero-Ibañez and A. Reyes-Muñoz, "Monitoring tomato leaf disease through convolutional neural networks," Electronics, vol. 12, 229, 2023. https://doi.org/10.3390/electronics12010229.

[10] L. Alzubaidi, J. Zhang, A. J. Humaidi, A. Al-Dujaili, Y. Duan, O. Al-Shamma, J. Santamaría, M. A. Fadhel, M. Al-Amidie, and L. Farhan, "Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions," J. Big Data, vol. 8, 53, 2021. https://doi.org/10.1186/s40537-021-00444-8.

[11] Y. Jiang, J. Xie, and D. Zhang, "An adaptive offset activation function for CNN image classification tasks," Electronics, vol. 11, 3799, 2022. https://doi.org/10.3390/electronics11223799.

[12] J. Chen, J. Chen, D. Zhang, Y. Sun, and Y. A. Nanehkaran, "Using deep transfer learning for image-based plant disease identification," Comput. Electron. Agric., vol. 173, 105393, 2020. https://doi.org/10.1016/j.compag.2020.105393.

[13] R. S. Ramos, L. Kumar, F. Shabani, and M. C. Picanço, "Risk of spread of tomato yellow leaf curl virus (TYLCV) in tomato crops under various climate change scenarios," Agric. Syst., vol. 173, pp. 524–535, 2019. https://doi.org/10.1016/j.agsy.2019.03.020.

[14] A. Dash, P. K. Sethy, and S. K. Behera, "Maize disease identification based on optimized support vector machine using deep feature of DenseNet201," J. Agric. Food Res., vol. 14, 100824, 2023. https://doi.org/10.1016/j.jafr.2023.100824.

[15] A. Mezenner, H. Nemmour, Y. Chibani, and A. Hafiane, "Tomato plant leaf disease classification based on CNN features and support vector machines," in Proc. 2022 2nd Int. Conf. Adv. Electr. Eng. (ICAEE), Constantine, Algeria, 29–30 Oct. 2022, pp. 1–5.

[16] J. Minango, M. Zambrano, W. Paredes Parada, C. Tasiguano, and K. Ayala, "Identification of corn leaves diseases images using MobileNet architecture in smartphones," in Proc. Trends Artif. Intell. Comput. Eng., Riobamba, Ecuador, 10–12 Nov. 2021, M. Botto-Tobar, O. S. Gómez, R. Rosero Miranda, A. Díaz Cadena, and W. Luna-Encalada, Eds., Springer Nature, Cham, Switzerland, 2023, pp. 661–673.