AI-Driven Hybrid Feature Fusion for Improved Coffee Leaf Disease Detection in IoT-Enabled Python Systems

Coffee, a commodity of global importance, is the second-most traded product and is widely consumed across the globe. Nevertheless, the leaves of the coffee plant are susceptible to fungal infections and insect infestations, which impair their photosynthetic areas and result in inferior, damaged coffee beans. The precise and prompt identification of these illnesses is essential for executing appropriate remedial actions since various species need distinct treatments, including pesticides or other methods. Accurate identification enables the implementation of suitable measures to avert more plant damage, safeguarding agricultural production and quality. This study uses deep learning methodologies to create an enhanced disease-detection system for coffee leaves. The proposed network incorporates an inception module for feature extraction, a global context module to capture spatial relationships, and a multi-head attention module to improve classification accuracy. This hybrid model facilitates the effective detection of coffee leaf diseases, demonstrating strong performance across various environmental circumstances. The solution Utilizes IoT-integrated Python systems for real-time application, enabling accessibility for coffee producers and supporting prompt decision-making. The system seeks to enhance crop management, Minimize losses, and promote sustainable agricultural practices by tackling disease detection difficulties using advanced AI technology.