Résumé:
Modern agriculture faces major challenges, including cereal leaf diseases, reduced crop yields, and the impacts of climate change. To address these issues, we developed AgriSense, an innovative system for the early detection of cereal diseases using deep learning and computer vision. AgriSense is based on a sequential master-slave architecture, where the first model determines whether a cereal plant is healthy or infected, and subsequent models identify the specific disease. The system can detect 11 critical diseases affecting wheat, maize, and rice, including brown rust, yellow rust, septoria, and leaf rust in wheat ; wilting, common rust, and gray leaf spot in maize ; as well as bacterial leaf blight, brown spot, leaf blast, and sheath blight in rice. By enabling fast and accurate diagnosis through a user-friendly interface, AgriSense helps farmers take timely action, reduce crop losses, and promote sustainable agricultural practices. This work highlights the potential of deep learning to revolutionize agri
