Deep Learning Based on NASNet for Plant Disease Recognition Using Leave Images

Global food security has become a very important research focus. This is due to the fact that food is a basic need of human beings and its adequate supply to meet the need of humans must be ensured. Plant diseases have, however, been one of the major problems threatening the adequate supply of food to humans. The early detection of these diseases can assist in their efficient management, thus making huge differences between survival and destruction of crops in farmlands affected by these plant diseases. Deep neural networks have been successfully applied in the field of artificial intelligence. This has inspired an increased research into the use of deep learning in the domains of image processing and computer vision. This paper present a study on the use of deep learning-based approach to identify diseased plants using leaf images by transfer learning. The study uses NASNet architeure for the convolutionary neural networks (CNN). The model is then trained and tested using a publicly available PlantVillage project dataset that contains varied images of plant leaves with multiple variations in infection status and location in the plants. Using the model, an accuracy rate of 93.82% was achieved.