The Deep Learning Based Analysis and Prediction of Apple Scab Disease in Apple Plants using ResNet-50 Hybrid Algorithm

Apple scab, caused by the fungus Venturia inaequalis, primarily affects the apple trees and the crab apples. It first emerges as dark, and velvety spots on leaves, fruits, and occasionally young twigs. This disease typically is revealed in thespring and thrives in the cool and moist environments. The fruit plantations with infections develop lesions that may break and deform, and infected leaves may become distorted and prematurely fall off. To control apple scab, the resistant varieties should be planted, pruning should be done to improve the air flow, and fungicides should be applied at key points during the growing season to protect new growth and mature fruit. This study introduces a deep-learning classifier designed to distinguish between two types of image data, one showing the apple leaves affected by apple scab disease and the other showing healthy apple leaves. The images undergo de-noising to improve quality. The cleaned data is then used to train ResNet50 networks, achieving high precision. In summary, this research aims to develop a highly accurate image classifier for detecting apple scab disease, achieving an accuracy rate of 90.67%.