Robust Plant Segmentation from Challenging Background with a Multiband Acquisition and a Supervised Machine Learning Algorithm

Taha Jerbi, Aaron Velez Ramirez, Dominique Van Der Straeten

2018

Abstract

Remote sensing through imaging forms the basis for non-invasive plant phenotyping and has numerous applications in fundamental plant science as well as in agriculture. Plant segmentation is a challenging task especially when the image background reveals difficulties such as the presence of algae and moss or, more generally when the background contains a large colour variability. In this work, we present a method based on the use of multiband images to construct a machine learning model that separates between the plant and its background containing soil and algae/moss. Our experiment shows that we succeed to separate plant parts from the image background, as desired. The method presents improvements as compared to previous methods proposed in the literature especially with data containing a complex background.

Download


Paper Citation


in Harvard Style

Jerbi T., Velez Ramirez A. and Van Der Straeten D. (2018). Robust Plant Segmentation from Challenging Background with a Multiband Acquisition and a Supervised Machine Learning Algorithm. In Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2018) - Volume 2: BIOIMAGING; ISBN 978-989-758-278-3, SciTePress, pages 100-105. DOI: 10.5220/0006552001000105


in Bibtex Style

@conference{bioimaging18,
author={Taha Jerbi and Aaron Velez Ramirez and Dominique Van Der Straeten},
title={Robust Plant Segmentation from Challenging Background with a Multiband Acquisition and a Supervised Machine Learning Algorithm},
booktitle={Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2018) - Volume 2: BIOIMAGING},
year={2018},
pages={100-105},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006552001000105},
isbn={978-989-758-278-3},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2018) - Volume 2: BIOIMAGING
TI - Robust Plant Segmentation from Challenging Background with a Multiband Acquisition and a Supervised Machine Learning Algorithm
SN - 978-989-758-278-3
AU - Jerbi T.
AU - Velez Ramirez A.
AU - Van Der Straeten D.
PY - 2018
SP - 100
EP - 105
DO - 10.5220/0006552001000105
PB - SciTePress