Plant diseases constitute a severe threat to yields and frequently cause enormous losses for the agricultural industry, which depends heavily on plant health for maximum crop yield. Due to the labor-intensive, time-consuming, and error-prone nature of conventional disease-diagnosing techniques like manual inspection, an automated real-time system that can precisely identify plant diseases at an early stage is required. This project offers a solution by integrating a camera with Raspberry Pi to enable real-time monitoring of plant conditions, which are then analyzed using the deep learning-based ResNet-50 model to precisely identify plant ailments. During the initial stage, Raspberry Pi transfers the input to the cloud server where the ML model is trained, then it processes and seeks out diseases. By converting the cloud-based model to on-device processing in the next stage, the system is extended to perform the analysis directly on the Raspberry Pi for more effective outputs. This concept lowers the need for stable internet access and provides results immediately in the field. Our system integrates advanced AI algorithms and affordable hardware, offering enormous potential for precision agriculture. To lessen agricultural losses and guarantee higher outputs, our system attempts to send farmers instant notifications and useful insights. It would enable them to take timely action based on immediate results. Hence, our model attained a high classification accuracy of 97%, accurately recognizing conditions such as healthy and diseased plants while reducing incorrect positives and negatives.