Detection and classification of Mango Leaf diseases utilizing convolutional neural network models

Abstract

Plant diseases, particularly those affecting crop plants, pose a significant danger to world food security by compromising the quality and yield of agricultural produce. Mango leaf disease is one such example. Mango leaf diseases are quite harmful since they can significantly lower crop yields of mangos, both in quantity and quality. Therefore, it is critical to identify leaf diseases in crops like mangos as soon as possible in order to take prompt preventive action. In large cultivated areas where mangoes are planted in significant quantities, the amount of manual inspection can be significantly reduced by mechanizing the process of disease recognition. With their exceptional ability to identify complex patterns in images, Convolutional Neural Networks (CNN) have great potential for automating the identification of illnesses affecting mango leaves. CNNs have been used in several studies with impressive accuracy rates, opening the door to improved crop management techniques and early disease diagnosis. In order to identify various illnesses, a research study using CNN—one of the most advanced deep learning algorithms—is presented in this work. CNN is used to segment and classify pictures of mango leaves. A number of CNN models, including Xception, MobileNetV2, ResNet50, DenseNet201, and ResNet50, have been used to accurately identify and categorize diseases, which will ultimately improve the production and health of mango crops. MangoLeafBD, a dataset that was acquired from Kaggle, has been used, and XAI (Explainable Artificial Intelligence), specifically Grad-CAM (Gradient-weighted Class Activation Mapping) and LIME (Local Interpretable Model-agnostic Explanations), were used to understand the rationale behind the decisions made by the applied models. Using these CNN models approach, it was observed that ResNet50 performs better than other models with 98% F1 score in identification and classification of mango leaf diseases.