INTERNATIONAL JOURNAL FOR INNOVATIVE RESEARCH IN MULTIDISCIPLINARY FIELD

Abstract:    Apple cultivation plays a vital role in the horticultural economy of many countries, including India, where crop productivity is significantly affected by fungal, bacterial, and viral diseases. Traditional disease identification methods mainly rely on visual inspection by experts, which are often time-consuming, labor-intensive, subjective, and less effective during early disease stages. Recent advancements in Machine Learning (ML) and Deep Learning (DL) techniques have transformed plant disease diagnosis by enabling automated, accurate, and real-time detection systems. This study presents a refined review and conceptual framework for apple leaf disease detection using ML and DL approaches. Various image-processing techniques, feature extraction methods, and classification algorithms such as Support Vector Machine (SVM), Random Forest (RF), Artificial Neural Network (ANN), Convolutional Neural Network (CNN), AlexNet, VGGNet, ResNet, GoogLeNet, and EfficientNet are critically analyzed for disease identification and classification. Publicly available datasets including PlantVillage and custom field datasets are discussed to evaluate the performance of different models under controlled and real-field conditions.