Irish Potato Imagery Dataset for Early Detection of Crop Diseases
Creators
- 1. Mbeya University of Science and Technology (MUST)
- 2. Nelson Mandela African Institution of Science and Technology (NM-AIST)
- 3. DevData Analytics
- 4. Makerere AI Lab
- 5. Tanzania Agricultural Research Institute (TARI)
- 6. Southern Corridor Alliance of Agriculture Producers (SCAAP)
Description
The annotated dataset consists of irish potatoes leaf imagery for early diseases detection. The irish potato crop leaves images were taken in Mbeya region in the Southern Highlands of Tanzania between 22nd November 2022 and 08th April 2023 using a mobile data collection tool, called the Open Data Kit (ODK). The crop leaf imagery dataset use case is developing machine learning models and end-user tools for early detection of (i) Early blight, and (ii) Late blight diseases in irish potatoes. The common leaf imagery data was collected from small holder farms using Samsung Galaxy A03 Core smartphones.
All images are in the .zip files; “lateblt.zip” has 20,499 images, “healthy.zip” has 20,438 images, and “earlyblt.zip” has 17,772 images. A total of 58,709 image files are labelled.
This research project is financially supported by the International Development Research Centre (IDRC) and the Swedish International Development Cooperation Agency (SIDA) through the Artificial Intelligence for Agriculture and Food Systems Innovation Research Network (AI4AFS-IRN) administered by the African Technology Policy Studies Network (ATPS) with Grant Award Number: AI4AFS/GA/AFS-2504001568.