A Standardized Method for Identifying and Categorizing Ladyfinger Diseases

Researchers provide a machine-learning approach that accurately classifies ladyfinger leaf illnesses. A 4380-photo dataset underpins the technique. Ladyfinger leaves in a variety of conditions in this dataset. In the table below, the model’s accuracy, recall, and F1-Score for healthy and unhealthy leaves are impressive. All values exceed $96.39 \%$. Support values show that the dataset is balanced, which helps the model’s generalization. The model’s $97.57 \%$ accuracy in diagnosing ladyfinger leaf illnesses is noteworthy. The macro, weighted, and micro averages show the model’s consistent performance across assessment criteria. This research advances automated plant disease diagnosis, showing how machine learning could improve agricultural processes. This model might help farmers because of its high accuracy and precision. This reliable method for early disease diagnosis and intervention helps apply sustainable crop management practices.