ARCHIVES

Agriculture plays a fundamental role in global food security, yet crop yields are continuously threatened by a wide range of plant diseases. Traditional disease identification methods rely heavily on manual inspection, which is time-consuming, error-prone, and not scalable for large-scale farming. This project proposes an automated plant disease recognition system using deep learning techniques to improve early detection and diagnosis. The approach leverages a Convolutional Neural Network (CNN) model trained on images of healthy and diseased plant leaves from publicly available datasets such as PlantVillage. Advanced preprocessing techniques, including image normalization and data augmentation, are applied to enhance model generalization. The model is trained and evaluated using PyTorch, and its performance is validated through accuracy metrics and confusion matrices. For practical usability, the trained model is deployed via a graphical user interface (GUI) built using Flask or Streamlit, enabling real-time disease classification through simple image uploads. The proposed solution demonstrates high accuracy and efficiency, showcasing the potential of artificial intelligence in advancing precision agriculture and supporting farmers with accessible, data-driven tools for plant health monitoring.