The Nelson Mandela African Institution of Science and Technology Maize dataset
Mduma, Neema; Nakatumba-Nabende, Joyce; Laizer, Hudson; Loyani, Loyani; Macheli, Mbwana; Msengi, Zablon; Karama, Alice; Msaki, Irine; Sanga, Sophia; Jomanga, Kennedy
About the Dataset
The maize images dataset was created to contribute to the study of maize diseases diagnostics. The images target the diagnostics of Maize Lethal Necrosis (MLN) and Maize Streak Virus (MSV) diseases. We are motivated in developing end to end tools to help farmers diagnose diseases and improve maize productivity. The dataset was created to facilitate image classification and object detection tasks.
The maize leaves images dataset can be used for various computer vision tasks such as image segmentation, image object detection, and image classification. These tasks promise to reduce bias from the background on the images when training on deep convolutional neural networks.