Plant disease significantly affects global agricultural productivity. Timely and accurate detection of leaf diseases can help farmers take corrective measures and prevent large-scale crop loss. In this study, we implement a deep learning approach using Convolutional Neural Networks (CNNs) and Transfer Learning with ResNet50 on the PlantVillage dataset to identify plant leaf diseases. A baseline CNN is first evaluated, followed by extensive experiments with ResNet50 using pre- trained ImageNet weights. The model is fine-tuned for classification of 38 plant disease categories. The performance is evaluated using standard metrics such as accuracy, precision, recall, and F1-score. Our approach achieved an overall test accuracy of 98% with robust generalization across various classes. Furthermore, visualizations using confusion matrices and class-wise precision support interpretability. This study confirms that transfer learning is an effective solution for plant disease classification and offers a scalable framework for agricultural diagnostics.
Vyas et al. (Wed,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: