부산대학교 도서관

Agriculture plays a crucial role in sustaining human life, and the global food supply is vulnerable to the devastating impact of plant diseases. The increasing threat to global food security due to plant diseases necessitates the development of efficient and accurate methods for early disease detection. Timely and accurate detection of diseases in crops is critical for ensuring food security and minimizing economic losses. Conventional approaches are time-consuming and may not scale effectively. This paper proposes three deep learning methos namely MLP, Convnets and Densenets for plant disease detection. A plant disease dataset from Kaggle was collected. The dataset consists of 25 classes of images five categories of plants namely apple, corn, tomato, potato and grape. The original dataset is divided into five datasets and three deep learning techniques namely Multi-Layer Perceptron, Convents and Densenets area applied. The experiments revealed that that Convnets performed better for apple, corn, grape and potato datasets disease classification and Densenet performed well for tomato dataset.