A Labeled Dataset of Healthy and Diseased Common Beans from Tanzania

The common bean images dataset was developed to advance research in diagnosing key bean diseases and boosting crop productivity. Sponsored by GrowFurther and carried out by researchers at the Nelson Mandela African Institution of Science and Technology (NM-AIST) in collaboration with the Tanzania Agriculture Research Institute (TARI), the project produced a labeled dataset featuring leaf images of healthy beans, Bean Anthracnose and Bean Rust. The dataset supports both image classification and object detection tasks.

All images are in the .zip files; “anthra.zip” has 13,542 images, “rust1.zip” has 10,300 images, “rust2.zip” has 10,307 images, “healthy1.zip – healthy10.zip” files each has 11,000 images, and “healthy11.zip” has 11,693 images. A total of 155,842 leaf image files are labelled.