Dataset of infected date palm leaves for palm tree disease detection and classification.

Autor:	Namoun A; AI Centre, Faculty of Computer and Information Systems, Islamic University of Madinah, Madinah 42351, Saudi Arabia., Alkhodre AB; AI Centre, Faculty of Computer and Information Systems, Islamic University of Madinah, Madinah 42351, Saudi Arabia., Sen AAA; Smart Cities, University of Prince Mugrin, Al-Madinah, Saudi Arabia., Alsaawy Y; AI Centre, Faculty of Computer and Information Systems, Islamic University of Madinah, Madinah 42351, Saudi Arabia., Almoamari H; AI Centre, Faculty of Computer and Information Systems, Islamic University of Madinah, Madinah 42351, Saudi Arabia.
Jazyk:	angličtina
Zdroj:	Data in brief [Data Brief] 2024 Sep 11; Vol. 57, pp. 110933. Date of Electronic Publication: 2024 Sep 11 (Print Publication: 2024).
DOI:	10.1016/j.dib.2024.110933
Abstrakt:	This article presents an image dataset of palm leaf diseases to aid the early identification and classification of date palm infections. The dataset contains images of 8 main types of disorders affecting date palm leaves, three of which are physiological, four are fungal, and one is caused by pests. Specifically, the collected samples exhibit symptoms and signs of potassium deficiency, manganese deficiency, magnesium deficiency, black scorch, leaf spots, fusarium wilt, rachis blight, and parlatoria blanchardi. Moreover, the dataset includes a baseline of healthy palm leaves. In total, 608 raw images were captured over a period of three months, coinciding with the autumn and spring seasons, from 10 real date farms in the Madinah region of Saudi Arabia. The images were captured using smartphones and an SLR camera, focusing mainly on inflected leaves and leaflets. Date palm fruits, trunks, and roots are beyond the focus of this dataset. The infected leaf images were filtered, cropped, augmented, and categorized into their disease classes. The resulting processed dataset comprises 3089 images. Our proposed dataset can be used to train classification deep learning models of infected date palm leaves, thus enabling the early prevention of palm tree-related diseases. (© 2024 The Authors.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu