Plant Disease Prediction using Transfer Learning Techniques

Abstract

Plant diseases are a significant hazard to feed a growing population, but due to a lack of infrastructure in many regions of the world, timely detection is challenging. Finding and detecting plant illness is essential in agricultural production. It takes a great deal of time and effort to find the disease. Agricultural sector can also reap the benefits of machine learning and deep learning. There has been a recent rise in the use of ML & DL techniques in plant disease identification. In this paper, we applied transfer learning technique for plant disease prediction. We used a ‘plantvillage’ dataset collected from Kaggle. Images of fifteen different types of plant leaves (Tomato, Potato, Pepper bell), from three distinct plants are included in this collection. We split the original dataset into three parts for three different plants and applied three transfer learning techniques VGG16, RESNET50, Inception and achieved accuracy of 98.7%, 98.6%, 99% respectively. The results of experiments shown that our proposed model achieved good accuracy when compared to traditional models.