Low-cost convolutional neural network for tomato plant diseases classifiation

<span lang="EN-US">Agriculture is a crucial element to build strong economy, not only because of its importance in providing food, but also as source raw materials for industry well energy. Different diseases affect plants, which leads decrease productivity. In recent years, developments computing technology and machine-learning algorithms (such deep neural networks) the field agriculture have played great role face this problem by building early detection tools. paper, we propose an automatic plant disease classification based on low complexity convolutional network (CNN) architecture, faster on-line classification. For training process, used more than one 57.000 tomato leaf images representing nine classes, taken under natural environment, considered during without background subtraction. The designed model achieves 97.04% accuracy less 0.2 error, shows high distinguishing from another.</span>