Makerere University Beans Image Dataset
Mugalu, Ben-Wycliff; Nakatumba-Nabende, Joyce; Katumba, Andrew; Babirye, Claire; Tusubira, Francis-Jeremy; Mutebi, Chodrine; Nsumba, Solomon; Namanya, Gloria
About the Dataset
This beans dataset was created to provide an open and accessible, well labeled, sufficiently curated image dataset. This is to enable researchers to build various machine learning experiments to aid innovations that may include; bean crop disease diagnosis and spatial analysis. This beans image dataset was collected across three different classes: Healthy, Angular Leaf Spot (ALS), and Bean Rust
Despite the fact that the agricultural sector is a national economic development priority in sub-Saharan Africa, crop pests and diseases have been the challenge affecting major food security crops like beans. In 2020, a study conducted on bean rust in Uganda showed that the disease resulted in an estimated loss of 5% to 67% in the six varieties considered for the study. In 2017 a study on Angular Leaf Spot and its sources in the sub-Saharan African region showed that the disease contributed an extreme yield loss estimated at 384.2 tons per year in the whole region. The current state of data collection and crop pest and disease diagnosis is transitioning from disease identification using visible symptoms to the use of data-driven solutions applying machine learning and computer vision techniques. Smallholder farmers and agricultural experts are equipped with mobile phones loaded with software to automatically collect field-level Geo-coded and time-stamped data. However, the image data previously collected has not been well-curated and shared with the wider machine learning community. In this dataset we a beans dataset of 5000 images for each class for the healthy, Angular Leaf Spot and Bean Rust classes.