Machine Learning Approaches for Leaf Disease Diagnosis and Edge Detection in Precision Agriculture with FPGA Integration

Plant diseases significantly threaten agricultural production, impacting crop quantity and quality. Millions of tons of crops are destroyed annually, leading to economic losses and food security concerns. Conventional management practices like chemical treatments and crop rotation have drawbacks, including environmental effects and pathogen resistance. To address these challenges, the Machine Learning approach proposes a real-time computer vision-based system for plant disease detection. Additionally, edge AI technology enables local data processing, reducing reliance on centralized servers and improving reliability in diverse field conditions. Comparative assessments will be conducted against conventional and AI-based alternatives, evaluating accuracy, cost-effectiveness, and efficiency. A system with edge AI integration advances precision agriculture by optimizing resource use, improving crop health management, and enhancing smart farming practices. To ensure fast processing of the developed system in real time, it is tested on the Xilinx Zynq SoC FPGA kit, and the results are subsequently validated.