Comparative Analysis of Tomato Leaf Disease Detection Using Machine Learning
Shruti Agnihotri, J. Datta Gupta, Neha Garg, Pallavi Khatri
Abstract
Disease transmission from affected crops to unaffected crops is getting the most dangerous things to agriculture. Epidemics spread like wildfire can affect entire farms if not spotted early. The plant disease detection method helps to identify infected plants at a very early stage and also helps users to extend plant disease identification for a variety of plants in an efficient manner. The purpose for work is to test the data using different machine learning models, Convolutional Neural Networks (CNN), K Nearest Neighbors (KNN), Visual Geometry Group (VGG-19), and apply them to plant disease detection on tomato leaves. The results on the implementation of machine learning models show that the KNN model performs better on every evaluation indicator.