Plant diseases present a major challenge to agricultural productivity and food security, highlighting the need for early detection to prevent significant crop loss. This project focuses on the use of Artificial Intelligence (AI) and Machine Learning (ML) to effectively detect and classify plant diseases. By utilizing Convolutional Neural Networks (CNNs), specifically the ResNet-50 architecture, along with Transfer Learning and Support Vector Machines (SVMs), we have developed a reliable system for plant disease identification. ResNet-50, with its deep residual network structure, facilitates advanced feature extraction by allowing the model to operate across multiple layers without vanishing gradient issues. Transfer Learning further improves model performance by leveraging knowledge from pre-trained networks, while SVMs enhance classification accuracy by refining decision boundaries. This integrated approach allows the system to analyze various visual features—such as leaf texture, color, and shape—resulting in a high-accuracy tool for automated disease detection. Designed for real-time, scalable implementation, this system provides farmers and agricultural professionals with an effective tool for proactive plant health monitoring, contributing to sustainable agriculture and better crop management.