Wheat spikelet dataset

School of Computer Science @ University of Nottingham


Organ fruit
Number of images 500
Ground-truth yes
Other information

Scientific article(s)

Deep Learning for Multi-task Plant Phenotyping
Michael P. Pound, Jonathan A. Atkinson, Darren M. Wells, Tony P. Pridmore, Andrew P. French
2017 IEEE International Conference on Computer Vision Workshops (ICCVW), 2018 View paper


The Wheat 2017 dataset features approximately 500 images of mature wheat plants, grown in pots and captured in front of a black screen. The dataset includes annotations for all visible ears and spikelets, as well as classification on whether a given plant has an awned phenotype.

Share your experience

blog comments powered by Disqus