DETECTION OF READY-TO-HARVEST TOBACCO LEAVES FROM DRONE IMAGES USING DEEP LEARNING

Tobacco leaf curing is a crucial process that determines the quality, flavor, and aroma of the final product. Accurate identification of ready-to-harvest leaves is essential to ensure optimal curing results. However, traditional methods rely on manual inspection, which is time-consuming, labor-intensive, and prone to human error. To address these challenges, this project proposes an automated DL-based approach for detecting mature tobacco leaves using drone-captured images. A CNN is trained on a dataset of tobacco leaves at various maturity stages, enabling precise classification without manual intervention. The system leverages drone technology to efficiently cover large agricultural fields, reducing the reliance on human expertise while improving harvesting accuracy. By integrating real-time image analysis, the proposed approach enhances decision-making for farmers, leading to improved productivity, cost savings, and better-quality cured tobacco.