Olive Leaves Disease Detection and Classification using Deep Learning

Abstract

Plants play a vital role in our environment and food substantially. Many plants are part of our food chain. The olive plant is one of the most significant plants, and we are achieving many benefits from it. The disease that affects these plants harms the quality of the olive and reduces its productivity, which also negatively impacts the economy. The Early detection and classification of these diseases is a big Challenge for the farmers. The early identification and targeted interventions can reduce crop management costs, minimize pesticide use, and prevent losses. A standard dataset called Zeytin_224x224_Augmented repository is utilized in this research. The dataset is openly available on Kaggle. Timely and accurate disease identification is essential for growers' income and olive production quality. The methodology utilized in this study for evaluating and classifying the effectiveness of InceptionV3 in detecting olive leaf disease and classification. Inception V3, deep learning enables early disease detection, allowing for timely treatment and ensuring the long-term sustainability of olive farming. We proposed a deep-learning model, Inception V3 that achieves the highest accuracy of 98.8%.