Improving Plant Health through Early Detection and Intervention

Plant diseases are serious threats to harvests and crop health. In this work, we use Convolutional Neural Networks (CNNs) to create a system for automated plant disease diagnosis. The goal is to assist farmers and plant enthusiasts in early disease identification and pro-vide targeted supplement recommendations for effective treatment. The project leverages the power of deep learning and computer vision techniques to analyze plant images and detect signs of diseases. To train the CNN model, a broad dataset of plant photos in various healthy and diseased states is used. The images are pre-processed, resized, and fed into the network, which employs multiple convolutional and pooling layers to learn hierarchical and discriminative features. The project also encompasses the development of a user-friendly web-based interface using the Flask frame-work. Users can conveniently upload plant images through the interface and receive prompt disease detection results along with personalized supplement recommendations. The system aims to empower farmers, horticulturists, and plant caregivers with a reliable tool to enhance disease management and optimize plant health