Smart Farming with AI: Comparative Evaluation of CNN Models for Tomato Leaf Disease Classification

Syed Sohail Ahmed Shah; Mujeeb-u-Rehman Maree; Aftab Ahmed Chandio; Mujeeb-ur-Rehman Jamali

Authors

Syed Sohail Ahmed Shah GC University Hyderabad, Sindh, Pakistan
Mujeeb-u-Rehman Maree Institute of Mathematics and Computer Science, University of Sindh, Jamshoro, Sindh, Pakistan
Aftab Ahmed Chandio Institute of Mathematics and Computer Science, University of Sindh, Jamshoro, Sindh, Pakistan
Mujeeb-ur-Rehman Jamali GC University Hyderabad, Sindh, Pakistan

Keywords:

CNN, Deep Learning, Plant Disease Detection, Classification

Abstract

Tomato is a major agricultural crop cultivated worldwide; however, its production is severely threatened by a wide range of plant diseases, necessitating accurate and timely detection methods. In recent years, neural network–based computer software and mobile applications have emerged as effective tools for plant disease detection. In this study, three advanced convolutional neural network (CNN) architectures—ResNet-50, DenseNet-121, and InceptionV3—are comparatively analyzed to evaluate their effectiveness in identifying and classifying tomato diseases using the PlantVillage dataset. To enhance model robustness against real-world variability, comprehensive image preprocessing and data augmentation techniques were employed, including rotation, horizontal and vertical flipping, rescaling, shear transformation, and zooming. A systematic hyperparameter tuning strategy was adopted by experimenting with various combinations of learning rates, batch sizes, and optimizers to optimize training performance. Experimental results demonstrate that hyperparameter optimization significantly improves classification accuracy, with the ResNet-50 model achieving the highest accuracy of 98.2%, along with superior F1-score, precision, and recall values. DenseNet-121 and InceptionV3 also exhibited strong performance, although their results were comparatively lower than those obtained with ResNet-50. These findings underscore the effectiveness of transfer learning and fine-tuning strategies in the development of automated systems for plant disease detection and classification. The study highlights the strong potential of CNN-based architectures for scalable and accurate disease detection, offering valuable support to farmers for early diagnosis and improved crop management. Furthermore, the study identifies future research directions, including deployment under real field conditions and the exploration of additional deep learning architectures.

References

J. Sharma, “Optimizing Tomato Crop Health: Disease Detection with,” Proc. 5th Int. Conf. Smart Electron. Commun. ICOSEC 2024, pp. 1259–1264, 2024, doi: 10.1109/ICOSEC61587.2024.10722724.

S. A. A. Qadri, N. F. Huang, T. M. Wani, and S. A. Bhat, “Advances and Challenges in Computer Vision for Image-Based Plant Disease Detection: A Comprehensive Survey of Machine and Deep Learning Approaches,” IEEE Trans. Autom. Sci. Eng., vol. 22, pp. 2639–2670, 2025, doi: 10.1109/TASE.2024.3382731.

F. Bin Jashim, F. R. Refat, M. H. Karim, F. U. Mahmud, and M. I. H. Siddiqui, “Interpretable mango leaf disease detection using a hybrid CNN–transformer model with GLCM features,” Int. J. Sci. Res. Arch., vol. 15, no. 2, pp. 1518–1535, May 2025, doi: 10.30574/IJSRA.2025.15.2.1510.

H. J. Runhua Zhang, “Optimization Methods, Challenges, and Opportunities for Edge Inference: A Comprehensive Survey,” Electronics, vol. 14, no. 7, p. 1345, 2025, doi: https://doi.org/10.3390/electronics14071345.

N. S. K. V. Krishna Pratap, “Revolutionizing Plant Disease Detection in Leaves: An Innovative Hybrid ABOCNN Framework for Advanced and Accurate Identification,” Int. J. Adv. Comput. Sci. Appl., vol. 15, no. 2, 2024, doi: 10.14569/IJACSA.2024.0150226.

S. M. R. A. M. Rajibul Islam, Asif Mahmod Tusher Siddique, Amiruzzaman, Abdullah-Al-Wadud, “An Efficient Technique for Recognizing Tomato Leaf Disease Based on the Most Effective Deep CNN Hyperparameters,” Ann. Emerg. Technol. Comput., vol. 7, no. 1, 2023, [Online]. Available: https://aetic.theiaer.org/archive/v7/v7n1/p1.html

A. M. W. Hsing Chung Chen, “AlexNet Convolutional Neural Network for Disease Detection and Classification of Tomato Leaf,” Electronics, vol. 11, no. 6, p. 951, 2022, doi: https://doi.org/10.3390/electronics11060951.

Y. D. Radhika Bhagwat, “Comprehensive Multilayer Convolutional Neural Network for Plant Disease Detection,” Int. J. Adv. Comput. Sci. Appl., vol. 12, no. 1, 2021, doi: 10.14569/IJACSA.2021.0120125.

S. Y. Iftikhar Ahmad, Muhammad Hamid, “Optimizing Pretrained Convolutional Neural Networks for Tomato Leaf Disease Detection,” Complexity, 2020, doi: https://doi.org/10.1155/2020/8812019.

M. S. M. A. Reem Mohammed Jasim Al-Akkam, “Plants Leaf Diseases Detection Using Deep Learning,” Iraqi J. Sci., vol. 63, no. 2, 2022, [Online]. Available: https://ijs.uobaghdad.edu.iq/index.php/eijs/article/view/4064

J. S. L. Lih Poh LIN, “Detection and Categorization of Tomato Leaf Diseases Using Deep Learning,” Int. J. Appl. Sci. Technol. Eng., vol. 1, no. 1, 2023, doi: https://doi.org/10.24912/ijaste.v1.i1.282-291.

V. J. Supriya Shrivastav, “A Fusion Method for Detection and Classification of Diseases in Tomato Plants Using Swarm-based Deep Learning,” Int. J. Exp. Res. Rev., vol. 45, 2024, [Online]. Available: https://qtanalytics.in/journals/index.php/IJERR/article/view/3900

K. B. Kamaldeep Kaur, “Enhancing Plant Disease Detection using Advanced Deep Learning Models,” Indian J. Sci. Technol., vol. 17, no. 17, pp. 1755–1766, 2024, doi: 10.17485/IJST/v17i17.536.

C. Vengaiah and S. R. Konda, “Improving Tomato Leaf Disease Detection with DenseNet-121 Architecture,” Int. J. Intell. Syst. Appl. Eng., vol. 11, no. 3, pp. 442–448, Jul. 2023, Accessed: Nov. 13, 2025. [Online]. Available: https://ijisae.org/index.php/IJISAE/article/view/3194

M. B. Suren Kumar Sahu, “PLANT DISEASE CLASSIFICATION USING DENSENET-121 ARCHITECTURE AND FLASK,” JETIR, vol. 10, no. 9, 2023, [Online]. Available: https://www.jetir.org/view?paper=JETIR2309022

W. J. Jin Liang, “A ResNet50-DPA model for tomato leaf disease identification,” Front. Plant Sci., vol. 14, 2023, doi: https://doi.org/10.3389/fpls.2023.1258658.

A. S. Laxmi Upadhyay, “Evaluation of Enhanced Resnet-50 Based Deep Learning Classifier for Tomato Leaf Disease Detection and Classification,” J. Electr. Syst., vol. 20, no. 3s, 2024, [Online]. Available: https://journal.esrgroups.org/jes/article/view/1856

S. I. Jiraporn Thomkaew, “Improvement Classification Approach in Tomato Leaf Disease using Modified Visual Geometry Group (VGG)-InceptionV3,” Int. J. Adv. Comput. Sci. Appl., vol. 13, no. 12, 2022, doi: 10.14569/IJACSA.2022.0131244.