Copy of Development of standard protocols for leaf image analysis and evaluation of machine learning methods for nitrogen diagnosis in tropical grass pastures

In Brazil, despite the relevance of tropical grasses as food source for livestock, the poor management along with minimal or no nutrient replenishment to the soil are key drivers of pasture degradation. The N is recognized as the most limiting nutrient for pasture growth, and the current lack of research focused on its nutritional diagnosis is a critical point for pastures persistency and productivity, highlighting the need for the development of robust diagnostic methods. An effective artificial vision system using image analysis should consider procedures and methods capable of capture physiological, structural, and biophysical plant responses through the selected relevant features. In this way, the present project aims i) to define a standard protocol for image segmentation when using leaf images of tropical grass pastures; ii) to evaluate the impacts of RGB indices and texture features of tropical grasses aiming to identify the most promising features for optimal modeling N diagnosis from individual leaf images; and iii) to compare the generalization performance and identify the most promising machine learning models (and their configurations) for diagnosis of N status in tropical grass pastures.