A Review on Various Approaches used in Leaf Disease Detection

Computer Engineering

Global sustenance depends heavily on agricultural output, which artificial intelligence greatly contributes to increasing. The automated identification of leaf diseases is one such use. It might be difficult to diagnose leaf diseases with normal eyesight since sick leaves can seem very normal. These illnesses have the potential to significantly lower crop output quality in the absence of prompt and appropriate care. Early identification is therefore crucial for increasing productivity and guaranteeing proper treatment. As a cornerstone of machine learning (ML), deep learning (DL) is increasingly essential for the early detection and categorization of plant diseases. This paper looks at the latest developments in crop disease detection using convolutional neural networks (CNNs), transfer learning, and deep learning. The investigation of deep learning architectures, data sources, and different image processing methods used to manage imaging data comes first. With the recent use of various DL architectures and visualization tools, plant disease classification and symptom identification have become critical tasks. The paper also discusses a few open issues that must be answered in order to create automated systems for the practical identification of plant diseases in the field.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.