RoCoLe: A robusta coffee leaf images dataset for evaluation of machine learning based methods in plant diseases recognition

Abstract

In this article we introduce a robusta coffee leaf images dataset called RoCoLe. The dataset contains 1560 leaf images with visible red mites and spots (denoting coffee leaf rust presence) for infection cases and images without such structures for healthy cases. In addition, the data set includes annotations regarding objects (leaves), state (healthy and unhealthy) and the severity of disease (leaf area with spots). Images were all obtained in real-world conditions in the same coffee plants field using a smartphone camera. RoCoLe data set facilitates the evaluation of the performance of machine learning algorithms used in image segmentation and classification problems related to plant diseases recognition. The current dataset is freely and publicly available at https://doi.org/10.17632/c5yvn32dzg.2.

Plant phenotyping relevance

コーヒー葉の病害状態と重症度を画像・アノテーションとして収録し、植物病害認識手法の評価用データセットとして提供することが中心であるため、植物フェノタイピング手法文献に含める。

Code and data availability

The paper is a Data in Brief article introducing the RoCoLe dataset of 1560 annotated robusta coffee leaf images, explicitly stated as freely and publicly available on Mendeley Data with DOI 10.17632/c5yvn32dzg.2.