Comparative Study of Disease Detection in Plants using Machine Learning and Deep Learning

The prediction of the growth in population will be 7.2 billion to 9.6 billion in year 2100. To meet the demands of food from agriculture, we have to move fast to smart agriculture. We also have to improve the methods for early disease detection in agriculture smartly. Thus, we may increase the production in agriculture filed. In this paper, we discuss briefly the machine learning and deep learning method like CNN architecture based on transfer learning by training them on the available Plant Village dataset. This will help us to automate and reduce the delay in disease detection which was to be done by human specialists only. This paper discusses the working of pre-trained models like AlexNet and GoogleNet and shows that these pre-trained models perform better than the other machine learning and shallow deep learning models.