A systematic analysis of machine learning and deep learning based approaches for identifying and diagnosing plant diseases

In agriculture, one of the most challenging tasks is the early detection of plant diseases. It is essential to identify diseases early in order to boost agricultural productivity. This problem has been solved with machine learning and deep learning techniques using an automated method for detecting plant diseases on large crop farms which is beneficial because it reduces monitoring time. In this paper, we used the dataset "Plant Village" with 17 basic diseases, with a display of four bacterial diseases, two viral illnesses, two mould illnesses, and one mite-related disease. A total of 12 crop species are also shown with images of unaffected leaves. The machine learning approaches viz support vector machines (SVMs), gray-level co-occurrence matrices (GLCMs), and convolutional neural networks (CNNs) are used for the development of prediction models. With the development of backpropagation ANNs, artificial intelligence for classification has also evolved. A K-mean clustering operation is also used to detect disease based on the real-time leaf images collected.