Performance evaluation of a custom convolutional neural network fordiagnosing mite infestation and diseases in tomato (Solanum lycopersicum L.)
DOI:
https://doi.org/10.24154/jhs.v20i2.3321Keywords:
Accuracy, convolutional neural network model, execution time, tomato leaf diseasesAbstract
A customized convolutional neural network (CNN) model is developed and fine-tuned for identifying tomato leaf diseases. The model is optimized by adjusting hyperparameters, batch size, and CNN layers. It is tested against mite infestation and ten diseases, including one bacterial, two viral, and seven fungal diseases. Compared to other models, customized CNN based model performed well both in terms of accuracy and execution time. Performance was analysed using loss-accuracy graphs and a confusion matrix. Evaluation metrics for test images from the original dataset showed an average accuracy, precision, recall, and F1 score of 99.64 per cent, with datasets for bacterial spot, leaf curl virus, leaf mould, Cercospora leaf spot, mosaic virus, and verticillium wilt achieving 100 per cent in these metrics. Dataset for two-spotted mite infestations also showed 100 per cent accuracy in recognising the damage. The execution time of custom CNN model on the tomato leaf disease dataset averaged 1339.09 seconds after 25 epochs, 1356.91 seconds after 50 epochs, and 2696 seconds in total for training across mite infestation and ten disease classes. The model accurately identified all 595, 896, 266, 56, 105, 575 diseased images of bacterial spot, leaf curl, leaf mould, Cercospora leaf spot, mosaic virus, verticillium wilt and 1981 images of two-spotted mite infested leaves, as well as 448 healthy images. These results demonstrate that the customized CNN model is highly effective and efficient in diagnosing mite infestation and a variety of tomato leaf diseases, offering a reliable tool for disease management.
Downloads
References
Abbas, A., Jain, S., Gour, M., & Vankudothu, S. (2021). Tomato plant disease detection using transfer learning with C-GAN synthetic images. Computers and Electronics in Agriculture, 187, 106279. https://doi.org/10.1016/j.compag.2021.106279
Abouelmagd, L. M., Shams, M. Y., Marie, H. S., & Hassanien, A. E. (2024). An optimized capsule neural network for tomato leaf disease classification. EURASIP Journal on Image and Video Processing, 2024(2), 1–21. https://doi.org/10.1186/s13640-023-00618-9
Afifi, A., Alhumam, A., & Abdelwahab, A. (2020). Convolutional neural network for automatic identification of plant diseases with limited data. Plants, 10(1), 28. https://doi.org/10.3390/plants10010028
Afify, M., Loey, M., & Elsawy, A. (2022). A robust intelligent system for detecting tomato crop diseases using deep learning. International Journal of Software Science and Computational Intelligence, 14(1), 1–21. https://doi.org/10.4018/IJSSCI.304439
Agarwal, M., Singh, A., Arjaria, S., Sinha, A., & Gupta, S. (2020). ToLeD: Tomato leaf disease detection using convolutional neural network. Procedia Computer Science, 167, 293–301. https://doi.org/10.1016/j.procs.2020.03.225
Bengio, Y. (2012). Practical recommendations for gradient-based training of deep architectures. arXiv. https://arxiv.org/abs/1206.5533
Bouni, M., Douzi, K., Hssina, B., & Douzi, S. (2023). Deep learning identifies tomato leaf disease by comparing four architectures using two types of optimizers. Journal of Electrical and Computer Engineering, 1–6. https://doi.org/10.1155/2023/5051005
Brahimi, M., Boukhalfa, K., & Moussaoui, A. (2017). Deep learning for tomato diseases: Classification and symptoms visualization. Applied Artificial Intelligence, 31(4), 299–315. https://doi.org/10.1080/08839514.2017.1315516
Cagli, E., Dumas, C., & Prouff, E. (2017). Convolutional neural networks with data augmentation against jitter-based countermeasures. In Proceedings of the International Conference on Cryptographic Hardware and Embedded Systems (CHES 2017) (pp. 45–68). Springer. https://doi.org/10.1007/978-3-319-66787-4_3
Choudhary, M. K., & Hiranwal, S. (2021). Feature selection algorithms for plant leaf classification: A survey. In S. D. Purohit et al. (Eds.), Proceedings of the International Conference on Communication and Computational Technologies (pp. 657–669). Springer. https://doi.org/10.1007/978-981-15-5077-5_59
Emebo, O., Fori, B., Victor, G., & Zannu, T. (2019). Development of tomato septoria leaf spot and tomato mosaic diseases detection device using Raspberry Pi and deep convolutional neural networks. Journal of Physics: Conference Series, 1299(1), 012118. https://doi.org/10.1088/1742-6596/1299/1/012118
Foysal, M., Ferdouse, A., Islam, M. S., Abujar, S., & Hossain, S. A. (2020). A novel approach for tomato diseases classification based on deep convolutional neural networks. In Proceedings of the International Joint Conference on Computational Intelligence (pp. 583–591). Springer. https://doi.org/10.1007/978-981-13-7564-4_49
Gulati, A., Singh, A. P., & Chug, A. (2024). Disease recognition and prediction in tomato using machine learning algorithms. In Proceedings of the National Seminar on Opportunities & Challenges in Agriculture, Environmental & Biological Sciences for Global Sustainable Development (pp. 1–48).
Kandel, I., & Castelli, M. (2020). The effect of batch size on the generalizability of convolutional neural networks on a histopathology dataset. ICT Express, 6(4), 312–315. https://doi.org/10.1016/j.icte.2020.04.010
LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278–2324. https://doi.org/10.1109/5.726791
Masters, D., & Luschi, C. (2018). Revisiting small batch training for deep neural networks. arXiv. https://doi.org/10.48550/arXiv.1804.07612
Mikołajczyk, A., & Grochowski, M. (2018). Data augmentation for improving deep learning in image classification problems. In International Interdisciplinary PhD Workshop (IIPhDW) (pp. 117–122). https://doi.org/10.1109/IIPHDW.2018.8388338
Poojary, R. P., Raina, R., & Mondal, A. K. (2021). Effect of data augmentation on fine-tuned CNN model performance. IAES International Journal of Artificial Intelligence, 10(1), 84–92. https://doi.org/10.11591/ijai.v10.i1.pp84-92
Radiuk, P. (2017). Impact of training set batch size on the performance of convolutional neural networks for diverse datasets. Information Technology and Management Science, 20(1), 20–24.
Rangarajan, A. K., Purushothaman, R., & Ramesh, A. (2018). Tomato crop disease classification using pre-trained deep learning algorithm. Procedia Computer Science, 133, 1040–1047. https://doi.org/10.1016/j.procs.2018.07.070
Saini, M., & Seba, S. (2019). Comparison of deep learning, data augmentation and bag-of-visual-words for classification of imbalanced image datasets. In Communications in Computer and Information Science (Vol. 1035, pp. 561–571). Springer. https://doi.org/10.1007/978-981-13-9181-1_49
Sardogan, M., Tuncer, A., & Ozen, Y. (2018). Plant leaf disease detection and classification based on CNN with LVQ algorithm. In Proceedings of the 3rd International Conference on Computer Science and Engineering (pp. 382–385). https://doi.org/10.1109/UBMK.2018.8566635
Shoaib, M., Shah, B., El-Sappagh, S., Ali, A., Ullah, A., Alenezi, F., Gechev, T., Hussain, T., & Ali, F. (2023). Advanced deep learning models-based plant disease detection: A review of recent research. Frontiers in Plant Science, 14, 1158933. https://doi.org/10.3389/fpls.2023.1158933
Shorten, C., & Khoshgoftaar, T. (2019). A survey on image data augmentation for deep learning. Journal of Big Data, 6(60), 1–48. https://doi.org/10.1186/s40537-019-0197-0
Shruthi, U., Nagaveni, V., Arvind, C. S., & Sunil, G. L. (2022). Tomato plant disease classification using deep learning architectures: A review. In Proceedings of the Second International Conference on Advances in Computer Engineering and Communication Systems (ICACECS 2021) (pp. 153–169). Springer. https://doi.org/10.1007/978-981-16-7389-4_15
Sonika, Gulati, R., & Jangra, M. (2017). Incidence of Tetranychus urticae Koch on brinjal under field and screen house conditions. Emergent Life Sciences Research, 3(2), 16–22. https://doi.org/10.7324/ELSR.2017.321622
Vinayedula. (2023). How does epoch affect accuracy in deep learning model? GeeksforGeeks. https://www.geeksforgeeks.org/how-does-epoch-affect-accuracy-in-deep-learning-model/
Widiyanto, S., Fitrianto, R., & Wardani, D. T. (2019). Implementation of convolutional neural network method for classification of diseases in tomato leaves. In Proceedings of the 4th International Conference on Informatics and Computing. https://doi.org/10.1109/ICIC47613.2019.8985909
Zhang, K., Wu, Q., Liu, A., & Meng, X. (2018). Can deep learning identify tomato leaf disease? Advances in Multimedia, 1–10. https://doi.org/10.1155/2018/6710865
Downloads
Published
Data Availability Statement
None
Issue
Section
License
Copyright (c) 2025 A Gulati, A P Singh, A Chug, K Ahlawat (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Authors retain copyright. Articles published are made available as open access articles, distributed under the terms of the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License, which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original author and source are credited. 
This journal permits and encourages authors to share their submitted versions (preprints), accepted versions (postprints) and/or published versions (publisher versions) freely under the CC BY-NC-SA 4.0 license while providing bibliographic details that credit, if applicable.
. 
