Registration-Classification based Approach to Multimodal Plant Image Segmentation (RCS)

Introduction

RCS is a command-line tool which was developed to perform a fully automated segmentation of a pair of corresponding fluorescent (FLU) and visible light (VIS) images such as acquired with LemnaTec phenotypic screening facilities.

Key Features

The RCS tool performs affine registration of a pair of FLU/VIS images followed by subsequent separation of plant and marginal background regions using pre-trained classification models.

Downloads

download RCS 64-bit executable for Windows incl. FLU/VIS images examples (~1.3GB)
download RCS 64-bit executable for Linux incl. FLU/VIS images examples (~1.3GB)

By downloading, installing and/or using this software the user agrees with the following license conditions.

This software requires MATLAB run time libraries (2018b) to be installed:

MATLAB run time for Windows x64 (~2GB).
MATLAB run time for Linux (~2GB).

Windows users should also install the run-time components from the following link: https://www.microsoft.com/en-us/download/details.aspx?id=48145.

Some information on dependencies of the MATLAB run-time components in Linux can be found here: https://de.mathworks.com/matlabcentral/answers/358052-is-there-a-list-of-matlab-runtime-dependencies.

General hardware requirements for MATLAB applications can be found here: https://de.mathworks.com/support/requirements/matlab-system-requirements.html.
For processing of image files of the 4-8 MP size such as provided with the supplementary data, 8GB or more RAM is recommended.

How to use

After unpacking the above *.zip file into a dedicated folder, run the executable (e.g., rcs.exe on Windows, included *.sh script on Linux). RCS should be run using the following syntax:

rcs.exe vis_img.png flu_img.png bg_vis.png bg_flu.png vis_seg.png flu_seg.png class_model.mat show_figs

where rcs.exe is the name of the RCS executable file, vis_img.png and flu_img.png are input VIS and FLU images, bg_vis.png and bg_flu.png are the corresponding reference (empty background) images of the same size as vis_img.png and flu_img.png. vis_seg.png and flu_seg.png are the segmented output images that are written out by RCS. class_model.mat is the name of one of the classification models provided with the RCS file repository (see the 'models' directory), and show_figs is a string parameter controlling optional visualization of results ("yes" to show figures, otherwise "no"). Further details on how to use the RCS tool can be found in the RCS Quick Guide (3MB).

References

[1] Henke M, Junker A, Neumann K, Altmann T, Gladilin E. A two-step registration-classification approach to automated segmentation of multimodal images for high-throughput greenhouse plant phenotyping. Plant Methods 16 (2020) 95. https://dx.doi.org/10.1186/s13007-020-00637-x

Leibniz Institute of Plant Genetics and Crop Plant Research (IPK)
OT Gatersleben
Corrensstrasse 3
06466 Stadt Seeland,
Telefon: +49 (0)39482 50
Telefax: +49 (0)39482 5139
E-Mail: info@ipk-gatersleben.de
Internet: www.ipk-gatersleben.de