Annotated Image Datasets of Rosette Plants

Hanno Scharr, Massimo Minervini, Andreas Fischbach, Sotirios A. Tsaftaris

2014 · 53 citations · 26 references

Concepts

Abstract

While image-based approaches to plant phenotyping are gaining momentum, benchmark data focusing on typical imaging situations and tasks in plant phenotyping are still lacking, making it dicult to compare existing methodologies. This report describes a benchmark dataset of raw and annotated images of plants. We describe the plant material, environmental conditions, and imaging setup and procedures, as well as the datasets where this image selection stems from. We also describe the annotation process, since all of these images have been manually segmented by experts, such that each leaf has its own label. Color images in the dataset show top-down views on young rosette plants. Two datasets show dierent genotypes of Arabidopsis while another dataset shows tobacco (Nicoticana tobacum) under dierent treatments. A version of the dataset, described also in this report, is in the public domain at http://www.plant-phenotyping.org/CVPPP2014-dataset and can be used for the purpose of plant/leaf segmentation from background, with accompanying evaluation scripts. This version was used in the Leaf Segmentation Challenge (LSC) of the Computer Vision Problems in Plant Phenotyping (CVPPP 2014) workshop organized in conjunction with the

References

26