Data Augmentation from RGB to Chlorophyll Fluorescence Imaging Application to Leaf Segmentation of Arabidopsis Thaliana from Top View Images
Abstract
In this report we investigate various strategies to boost the performance for leaf segmentation of Arabidopsis thaliana in chlorophyll fluorescent imaging without any manual annotation. Direct conversion of RGB images to gray levels picked from CVPPP challenge or from a virtual Arabidopsis thaliana simulator are tested together with synthetic noisy versions of these. Segmentation performed with a state of the art U-Net convolutional neural network is shown to benefit from these approaches with a Dice coefficient between 0.95 and 0.97 on the segmentation of the border of the leaves. A new annotated dataset of fluorescent images is made available.
Cite
Text
Sapoukhina et al. "Data Augmentation from RGB to Chlorophyll Fluorescence Imaging Application to Leaf Segmentation of Arabidopsis Thaliana from Top View Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019. doi:10.1109/CVPRW.2019.00312Markdown
[Sapoukhina et al. "Data Augmentation from RGB to Chlorophyll Fluorescence Imaging Application to Leaf Segmentation of Arabidopsis Thaliana from Top View Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.](https://mlanthology.org/cvprw/2019/sapoukhina2019cvprw-data/) doi:10.1109/CVPRW.2019.00312BibTeX
@inproceedings{sapoukhina2019cvprw-data,
title = {{Data Augmentation from RGB to Chlorophyll Fluorescence Imaging Application to Leaf Segmentation of Arabidopsis Thaliana from Top View Images}},
author = {Sapoukhina, Natalia and Samiei, Salma and Rasti, Pejman and Rousseau, David},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2019},
pages = {2563-2570},
doi = {10.1109/CVPRW.2019.00312},
url = {https://mlanthology.org/cvprw/2019/sapoukhina2019cvprw-data/}
}