Abstract

Plant diseases pose a significant threat to agriculture by rapidly spreading across crops, reducing yields, diminishing food quality, and causing substantial financial losses for farmers. Traditional disease detection methods rely heavily on manual visual inspection by agricultural experts—a process that is often time-consuming, labor-intensive, and susceptible to human error. These limitations become even more pronounced in large-scale farming operations, where timely and accurate disease identification is critical. To address these challenges, this study introduces an advanced deep learning-based solution utilizing Convolutional Neural Networks (CNNs) integrated with the ResNet50 architecture for the accurate classification and identification of multiple plant diseases. ResNet50’s residual learning framework effectively mitigates the vanishing gradient problem, allowing for deeper model training and improved feature extraction. Trained on a comprehensive dataset of healthy and diseased plant leaf images, the model learns to detect subtle variations in texture, color, and pattern associated with various plant conditions. To enhance accessibility, a user-friendly web application built with Flask is developed, enabling real-time disease diagnosis through a simple image upload interface. This tool empowers farmers and agricultural professionals to receive instant insights into plant health, supporting more informed decision-making and proactive disease management. This work highlights the transformative potential of AI-driven solutions in precision agriculture, offering scalable, efficient, and sustainable methods for early disease detection and crop management.

References

• H. Durmus, E. O. Günes, and M. Kirci, ‘‘Disease detection on the leaves of the tomato plants by using deep learning,’’ in Proc. 6th Int. Conf. AgroGeoinformatics, Aug. 2017, pp. 1–5.
• A. Fuentes, S. Yoon, H. Youngki, Y. Lee, and D. S. Park, ‘‘Characteristics of tomato plant diseases—A study for tomato plant disease identification,’’ in Proc. Int. Symp. Inf. Technol. Converg, vol. 1, 2016, pp. 226–231.
• S. P. Mohanty, D. P. Hughes, and M. Salathé, ‘‘Using deep learning for image-based plant disease detection,’’ Frontiers Plant Sci., vol. 7, Sep. 2016, Art. no. 215232.
• H. T. Lin, Cherry Tomato ’TSS ASVEG No. 22’.Taiwan Seed Improvement and Propagation Station. Taichung, Taiwan: COA, 2017.
• E. Özbilge, M. K. Ulukök, Ö. Toygar, and E. Ozbilge, ‘‘Tomato disease recognition using a compact convolutional neural network,’’ IEEE Access, vol. 10, pp. 77213–77224, 2022.
• A. H. T. Rusli, B. C. C. Meng, N. S. Damanhuri, N. A. Othman, M. H. Othman, and W. F. A. W. Zaidi, ‘‘Potato leaf disease classification using image processing and artificial neural network,’’ in Proc. IEEE 12th Int. Conf. Control Syst., Comput. Eng. (ICCSCE), Oct. 2022, pp. 107–112.
• Q.-H. Phan, V.-T.Nguyen, C.-H.Lien, T.-P. Duong, M. T.-K. Hou, and N.-B. Le, ‘‘Classification of tomato fruit using YOLOv5 and convolutional neural network models,’’ Plants, vol. 12, no. 4, p. 790, Feb. 2023.
• P. Tim, A. Pranathi, K. SaiAshritha, N. B. Chittaragi, and S. G. Koolagudi, ‘‘Tomato leaf disease detection using convolutional neural networks,’’ in Proc. 11th Int. Conf. Contemp. Comput. (IC3), Aug. 2018, pp. 1–5.
• A. Dwivedi, A. Goel, M. Raju, D. Bhardwaj, A. Sharma, F. Kidwai, N. Gupta, Y. Sharma, and S. Tayal, ‘‘Precision agriculture: Using deep learning to detect tomato crop diseases,’’ in Proc. Int. Conf. Innov. Comput.Commun. Singapore: Springer, 2024, pp. 857–865.
• K. N. E A. Siddiquee, M. S. Islam, M. Y. U. Dowla, K. M. Rezaul, and V. Grout, ‘‘Detection, quantification and classification of ripened tomatoes: A comparative analysis of image processing and machine learning,’’ IET Image Process., vol. 41, pp. 2442–2456, Sep. 2020.
• Mohanty, S. P., Hughes, D. P., &Salathé, M. (2016). Using deep learning for image-based plant disease detection.Frontiers in Plant Science.
• Wang, G., Sun, Y., & Wang, J. (2017). Automatic image-based plant disease severity estimation using deep learning.Computational Intelligence and Neuroscience.
• M. E. Haque, A. Rahman, I. Junaeid, S. U. Hoque, and M. Paul, "Rice leaf disease classification and detection using YOLOv5," arXiv preprint arXiv:2209.01579, Sep. 2022. [Online]. Available: https://arxiv.org/abs/2209.01579Google Scholar+3
• S. A. Rashwan and M. K. Elteir, "Plant leaf disease detection using deep learning on mobile devices," Int. J. Comput. Vis. Robot., vol. 12, no. 2, pp. 156–176, Feb. 2022. [Online]. Available: https://www.inderscience.com/info/inarticle.php?artid=121151Inderscience+1AC
• S. S. S. R. K. Reddy, B. V. R. Reddy, and B. R. Reddy, "Tomato plant leaf disease segmentation and multiclass disease detection using hybrid optimization enabled deep learning," Computers and Electronics in Agriculture, vol. 209, p. 107849, Sep. 2023. [Online]. Available: https://pubmed.ncbi.nlm.nih.gov/37543108/.
• M. A. A. Khandaker, Z. S. Raha, S. Islam, and T. Muhammad, "Explainable AI-enhanced deep learning for pumpkin leaf disease detection: A comparative analysis of CNN architectures," in Proc. 27th Int. Conf. Comput. Inf. Technol. (ICCIT), Cox’s Bazar, Bangladesh, Dec. 2024.