Encouraging hygiene permanence in tomato leaf and applying machine learning techniques

Abstract

Tomatoes are the major ingredient in food preparation, which leads to a huge food production rate. Most countries cultivate huge tomatoes at the same time that crop diseases affect the production rate due to many different types of diseases. The various types of diseases are bacterial spots, septoria leaf spot, left mold, late blight, early blight, arget and spot. Many research studies review these tomato leaf diseases with various statistics. The survey on disease will give a clear idea of reasons and prevention methods, also presenting how to reduce it in the early stages. In another study, tomato leaf images were taken to classify the diseased and non-diseased varieties. Few studies compare the standard model of disease prediction with the machine learning models. Therefore, this research study discusses tomato leaf disease detection and prevention methods used by various researchers in their studies and finally consolidate the observations. This study also deals with encouraging hygiene permanence in tomato leaf using machine learning algorithms. The convolutional neural network (CNN) was used to predict the early nature of the hygiene nature of leafy vegetable plants for the benefit of agriculture people and concluded with better future suggestions.