DEEP LEARNING-BASED AUTOMATED SYSTEM FOREARLY DETECTION OF PLANT DISEASES

Abstract

Agriculture is an essential part of being human. It is possible that more than 60% of the population lives in agricultural regions in some way. Farmers consistently declined to increase crop production since the antiquated system could not identify illnesses in most agricultural goods. It is vital to recognize farming illnesses as soon as possible since they inhibit plant growth. Multiple Machine Learning (ML) methods have been developed for the purpose of identifying and classifying agricultural illnesses. Recent developments in Deep Learning (DL) and other forms of machine learning suggest that this area of research has the potential to grow considerably more nuanced. To reliably detect signs of agricultural diseases, the suggested approach employs a combination of deep and convolutional neural networks. We also use a number of efficiency indicators to evaluate these strategies. This post delves into the detailed examination of the deep learning algorithms that are utilized to predict the advent of crop diseases. If scientists are alert to certain knowledge gaps, they may be able to detect plant diseases long before any symptoms show up. The proposed approach will be used to build convolutional neural network technology that can identify plant diseases by analyzing their leaves.