Plant Disease Detection Using Deep Learning

Abstract

Abstract: Crop diseases are a major threat to food security, but their rapid identification remains difficult inmany parts of the world due to the lack of thenecessary infrastructure. The combination of increasing global smartphone penetration and recent advances in computer vision made possible by deep learning has paved the way for smartphone-assisted disease diagnosis. Using a public dataset of 54,306 images of diseased andhealthy plant leaves collected under controlled conditions, we train a deep convolutional neuralnetwork to identify 14 crop species and 26 diseases (or absence thereof). The trained model achieves anaccuracy of 99.35% on a held-out test set, demonstrating the feasibility of this approach. Overall, the approach of training deep learning models on increasingly large and publicly availableimage datasets presents a clear path toward smartphone-assisted crop disease diagnosis on a massive global scale