Lychee Tree Disease Classification and Prediction using Transfer Learning

Abstract

Bangladesh is a predominantly agricultural nation. The majority of people depend on agriculture. But it is a sad fact that the quality and quantity of our fruits are declining due to numerous diseases. People in our nation are discovering numerous new unusual diseases in our native fruits, but we are failing to diagnose these diseases, and the severity of this issue is growing daily. So, to combat this issue, suitable treatment or recuperation is required. Since we live in a technological age, it goes without saying that technology may be quite helpful in identifying these ailments. As the health of a plant depends on its leaves, it is crucial to first identify any tree diseases. As a result, we can prevent illness from spreading to the tree and fruit. We are trying to identify tree and leaf diseases through our research. Research into lychee tree disease is something we are highly interested in. Therefore, by preventing sickness in our lychee fruit, we can contribute to the Bangladeshi economy. We use cutting-edge image processing methods that are very beneficial to us to guarantee the freshness of the leaves. By simply looking at the leaves, it is quite difficult to identify any disease. Our system uses a cutting-edge method called image processing. For this, we use the method CNN (Convolutional Neural Network) based transfer learning classification algorithm. In this, we use the VGG16, InceptionV3, and Xception algorithm and as a result, the Inception-V3 model beat the other two models with a maximum accuracy of 92.67%, which indicate the successful outcome of this study.