AI Enabled Early-Stage Brinjal Leaf Disease Detection using Pre-Trained Models

Abstract

To correctly distinguish leaf diseases in eggplant (Solanum melongena), it is very important to improve agricultural production systems for precision. This paper presents a comparative analysis of five pre-trained convolutional neural network models, namely ResNet50, MobileNetV2, GoogLeNet, Xception, and VGG16, for multi-class classification of eggplant leaf diseases. In this work, a composite image dataset was developed by combining images from publicly available Kaggle , Mendeley repositories and local dataset (by collection from fields) to improve data diversity and generalization capability. A structurally optimized VGG16 model was developed to process 128 × 128 pixel images, which aimed to reduce computational complexity with preserved classification accuracy. Under the same training environment, the proposed modification achieved a classification accuracy of 96.5%. In addition to quantitative analysis, interpretability of the model was incorporated using Local Interpretable Model-agnostic Explanations (LIME) to generate localized feature attribution maps, thereby addressing the transparency problem associated with deep neural networks. The experimental results demonstrated that, although ResNet50 achieved the highest overall classification accuracy, the modified VGG16 architecture demonstrated a more balanced performance in terms of computational complexity, latency, and interpretability. Thus, the modified VGG16 is a reasonable candidate for use in real-time resource-constrained agricultural disease diagnostic system applications.