Virtual Booth

In hydroponic farming, crop production must be maximized by accurately diagnosing leaf diseases, although current manual detection techniques are vulnerable to inaccuracies. Using advanced image processing and deep learning techniques, this work develops an accurate, automated way to fill the gap in the literature on algorithms designed for hydroponic applications. Through preprocessing and algorithmic analysis of a wide range of tomato leaf images, the project seeks to develop new techniques, especially for hydroponic farming. To guarantee a plant health diagnostic system that works, these algorithms will be assessed for accuracy, precision, recall, and F1 scores. Through the improvement of disease control, crop production optimisation, and sustainability of urban hydroponic agriculture, the study hopes to produce an extremely precise and efficient automated plant health diagnostic system.