Plant Health Detection System using Deep-Learning

Abstract

Food security, environmental stability, and agricultural output are all significantly impacted by plant health. Expert visual inspection is a common component of traditional plant health assessment techniques, although it can be laborious, subjective, and prone to human mistake. Using advances in computer vision and machine learning, there has been an increasing interest in applying deep learning techniques for automated plant health diagnosis in recent years. This study provides a thorough analysis of deep learning- based plant health detection systems, covering a wide range of topics including model architectures, training methodologies, dataset collecting and preprocessing, and performance evaluation measures. The field's main obstacles and prospects are noted, such as the lack of datasets, the inability of the model to generalize to many plant species and environmental circumstances, and the inability of the model to scale to large-scale agricultural settings.