TY  - RPRT
ID  - eprints2270
EP  - 16
PB  - Forschungszentrum Julich
A1  - Scharr, Hanno
A1  - Minervini, Massimo
A1  - Fischbach, Andreas
A1  - Tsaftaris, Sotirios A.
N2  - 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 difficult 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 different genotypes of Arabidopsis while another dataset shows tobacco (Nicoticana tobacum) under different 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 13th European Conference on Computer Vision (ECCV), in Zürich, Switzerland. We hope with the release of this, and future, dataset(s) to invigorate the study of computer vision problems and the development of algorithms in the context of plant phenotyping. We also aim to provide to the computer vision community another interesting dataset on which new algorithmic developments can be evaluated.
M1  - technical_report
Y1  - 2014/07//
TI  - Annotated image datasets of rosette plants
AV  - none
UR  - http://hdl.handle.net/2128/5848
ER  -