Detection of Mealy Lice Disease Using Artificial Intelligence Methods

Abstract

Today, the need for agricultural lands has increased even more due to the increasing population density. For this reason, increasing the yield of crops in agricultural areas becomes a very important need. It is very important to minimize the pests that negatively affect plant productivity in agricultural areas. In the study, it was aimed to detect the mealybug disease, which negatively affects plant productivity in agricultural areas, by using artificial intelligence methods. 539 disease-bearing and disease-free plant images collected from open access websites were used. These images are classified by VGG-16, Resnet-34 and Squeezenet deep learning algorithms. The most successful among the three architectures was determined as the VGG-16 and ResNet-34 model with an accuracy rate of 97%.