Plant Disease Detection by Leaf Image Classification Using Convolutional Neural Network

Plants are the source of food Plants are the source of food on the planet. Infections and diseases in plants are therefore a serious threat, while the most common diagnosis is primarily performed by examining the plant body for the presence of visual symptoms. As an alternative to the traditionally time-consuming process, different research works attempt to find feasible approaches towards protecting plants. In recent years, growth in technology has engendered several alternatives to traditional arduous methods. Deep learning techniques have been very successful in image classification problems. This work uses Deep Convolutional Neural Network (CNN) to detect plant diseases from images of plant leaves and accurately classify them into 2 classes based on the presence and absence of disease. A small neural network is trained using a small dataset of 1400 images, which achieves an accuracy of 96.6%. The network is built using Keras to run on top of the deep learning framework TensorFlow.