Arabica coffee leaf images dataset for coffee leaf disease detection and classification.

Abstract

This article introduces Arabica coffee leaf datasets known as JMuBEN and JMuBEN2. Image acquisition was done in Mutira coffee plantation in Kirinyaga county-Kenya under real-world conditions using a digital camera and with the help of a pathologist. JMuBEN dataset contains three compressed folders with images inside. The first file contains 7682 images of Cerscospora, the second contains 8337 images of rust and the last one contains 6572 images of Phoma. JMuBEN2 contains two compressed files where the first file contains 16,979 images of Miner while the other contains 18,985 images of healthy leaves. In total, the dataset contains 58,555 leaf images spread across five classes (Phoma, Cescospora, Rust, Healthy, Miner,) with annotations regarding the state of the leaves and the disease names. The Arabica datasets contain images that facilitates training and validation during the utilization of deep learning algorithms for coffee plant leaf disease recognition and classification. The dataset is publicly and freely available at https://data.mendeley.com/datasets/tgv3zb82nd/1 and https://data.mendeley.com/datasets/t2r6rszp5c/1 respectively.

Plant phenotyping relevance

コーヒー葉の病害・健全状態を画像と注釈で体系化した公開データセットであり、植物表現型（病害状態）の取得・分類基盤が研究の中心である。

Code and data availability

The paper is a data descriptor for the JMuBEN and JMuBEN2 Arabica coffee leaf image datasets, which are the paper's own phenotyping assets (58,555 annotated leaf images across five classes) and are publicly available on Mendeley Data.