Harnessing Deep Learning for Tea Tree Leaf Disease Management: A CNN-SVM Perspective

The health and yield of the crops are affected, which presents serious problems for the tea business. Effective disease control and long-term tea production depend on early and precise disease identification. Anthracnose, blister blight, red rust, grey blight, brown blight, and orange spot are six prevalent diseases that affect tea tree leaves. In this study, the researchers suggest a unique method employing convolutional neural networks and support vector machines to forecast these illnesses. Precision, recall, F1-Score, support, as well as accuracy indicators, are used to assess the model's effectiveness. The CNN-SVM model distinguishes out with a remarkable 95.01 percent overall accuracy. The accuracy, recall, and F1-Score values, which range between 92.06% to 96.49%, further demonstrate the model's capacity to correctly identify diseases inflicting tea tree leaves. The study's conclusions highlight the model's potential as a trustworthy tool for tea farmers to identify and control infections, eventually assisting in the development of sustainable teagrowing practices. Future studies may concentrate on improving the model further and investigating new data augmentation strategies to improve its illness-detection skills.