Abstract: Plant leaf disease detection is a critical component of precision agriculture, aimed at improving crop health, maximizing yield, and minimizing losses caused by plant pathogens. Traditional disease identification methods rely heavily on manual inspection by agricultural experts, which is often time-consuming, labor-intensive, and prone to error, especially in large-scale farming operations. The integration of artificial intelligence (AI), particularly deep learning and computer vision techniques, has revolutionized this process by enabling automated, accurate, and real-time disease detection through the analysis of leaf images. This project presents an AI-driven system that utilizes Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and Explainable AI (XAI) to classify plant leaf diseases with high precision. The system incorporates image preprocessing, model inference, and result visualization, and can be deployed via mobile or web applications for ease of access by farmers. It is designed to work under diverse environmental conditions and supports real-time monitoring using IoT-enabled devices. Despite its effectiveness, the system faces challenges such as dataset limitations, environmental variability, and high computational demands. By addressing these issues through optimized models, data augmentation, and edge deployment strategies, the system aims to provide an accessible and scalable solution for disease detection in agriculture. Ultimately, this approach supports early intervention, reduces dependency on pesticides, and contributes to sustainable and smart farming practices.

Keywords: Plant Leaf Disease Detection

| DOI: 10.17148/IARJSET.2025.125370