Prediction of Groundnut Leaf Disease Detection and Classification-Comparative Review of Machine Learning Techniques and their Analysis

Abstract

The world's largest producer of groundnuts is India. The edible leguminous oilseed groundnut (Arachishypogaea L.) is a significant crops. The groundnut's economic productivity is constrained by Groundnut Diseases attack is a significant causing low yield. In comparison to many other crops, groundnut crops are far more susceptible to diseases assault. In this work, with the aim of enhancing production through disease prevention and detection in several agricultural domain sectors. We proposed a deep-learning-based technique for identifying Groundnut diseases and Classification in a variety of Leafs using the plant village dataset, with the goal of increasing production through disease prevention and detection in diverse agricultural domain sectors. Many researchers have worked upon Groundnut leaf disease diagnosis and prognosis; each approach has a distinct accuracy rate, which changes depending on the scenario and datasets utilized.Our primary goal is to compare several current ML & Deep Learning approaches in order to identify the best effective method that would support the huge dataset with high efficiency of Predictions for Groundnut Leaf Disease Detection.