A Generative AI–Driven IoT Framework for Automated Leaf Structure Analysis in Precision Farming

Precision farming needs precise, ongoing, and automated analysis of crop health, which the conventional image-based systems fail to do due to poor quality field images and unstable weather conditions. The proposed research aims to address these limitations by suggesting a Generative AI-powered IoT Framework of Automated Leaf Structure Analysis, which is a combination of sophisticated generative enhancement methods and real-time IoT monitoring. Generative model is a major breakthrough in the comprehension of the description of leaves, as it enhances the veins, image texture, and morphological boundaries of the leaves, hence making the extraction and classification of features more precise. IoT sensors provide continuous data capture and low transmission response and high system availability, which make them reliable at the field level. It is shown that the experimental evaluation showed significant gains in PSNR, SSIM and morphological stability and the hybrid classifier attains 96.8% accuracy, exceeding the accuracy of baseline CNN and deep-learning models.