Leaf Disease Detection using Deep Learning

Abstract

Agriculture plays an important role in determining India's economy. So, the detection of disease that affects the plants is most important as it affects productivity. The proposed system is designed to detect the diseases that degrade the health of the leaves. The diseases may be of bacterial, viral and late blight. The diseases can be detected with the help of Convolutional Neural Network (CNN). It is composed of several layers that help in the prediction of diseases. The designed CNN classifies the disease into three major categories. An input leaf image is provided to test whether the leaf is healthy or not. The system has been trained with different input leaves. Once it is trained the new input leaves are given to the classifier, then the classifier identifies the label of the affected leaves. Based on the disease identified, the necessary remedies can be taken for curing the disease.