Study on convolutional autoencoder using genetic algorithm for diagnosis of crop diseases

Abstract

Crop diseases are one of the factors contributing to crop yield loss..Because some of these diseases can cause damage to other crops, early detection is necessary. Not only detecting disease strains needs much, but it is also difficult for new farmers to distinguish them; it is necessary to automate the early detection of diseased strains. This paper proposes a disease strain detection method using CAE (convolutional autoencoder). Experimental results show that preprocessing the images and optimizing the CAE structure improved the accuracy.