Published December 18, 2016 | Version v1
Dataset Open

Library of simulated root images, with different noise levels

  • 1. Forschungszentrum Jülich, Université catholique de Louvain
  • 2. University of Amsterdam
  • 3. University of Liège
  • 4. INRA Avignon

Description

This depository contains the images and associated RSML files used in the paper entitled "Using a structural root system model to evaluate and improve the accuracy of root image analysis pipelines" from the same authors.

 

It contains: 

- 30.000 simulated root images of 10.000 different root systems, with different noise levels (0=null, 1=medium, 3=high);

- 10.000 corresponding RSML files;

- .csv files containing the ground-truth data for each modelled root system (500-data.csv);

- .csv files containing the image descriptors extracted using RIA-J (500-descriptors.csv);

 

The codes used to generate and analyse this dataset is available here: http://doi.org/10.5281/zenodo.208499

Note about the metrics computed from the RSML files (contained in 500-data.csv): the root systems were simulated in a constrained 2D space (rhizotron-like). Therefore, the RSML_reader plugin computed the lengths of the different roots in 2D only (despite the fact that a Z coordinate is present in the the RSML files). 

 

CORRECTION: There is a scale issue in the 500-descriptors.csv file. "area" and "convexhull" columns values should be divided by 10 

 

 

Files

500-data.csv

Files (31.6 GB)

Name Size Download all
md5:ddccf7a952ae13c284d95a470a38f27f
6.3 MB Preview Download
md5:1e4ef09d8b651c89207985c6d30dd32d
6.6 MB Preview Download
md5:38684bf19c992ae641574fa46409fad4
1.7 GB Preview Download
md5:baee281360cf3f1fa86f8586b40fd071
7.1 GB Preview Download
md5:8d2015975f7214984e2b52816ed1c29d
10.7 GB Preview Download
md5:8022fa8d69e70b23c5a1e7947cc9252f
384.1 MB Preview Download
md5:d8c94b03cff6dcb223127f718d0e8b65
662.8 MB Preview Download
md5:580f26b0eea78481bdd51cdb2edd9d8b
4.3 GB Preview Download
md5:c00d4619878de069616d75d4c07a7db8
6.7 GB Preview Download
md5:ced235ba9f73b5117013a395f153d1b5
148.7 MB Preview Download