% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Giuffrida:843816,
author = {Giuffrida, M. Valerio and Chen, Feng and Scharr, Hanno and
Tsaftaris, Sotirios A.},
title = {{C}itizen crowds and experts: observer variability in
image-based plant phenotyping},
journal = {Plant methods},
volume = {14},
number = {1},
issn = {1746-4811},
address = {London},
publisher = {BioMed Central},
reportid = {FZJ-2018-01356},
pages = {12},
year = {2018},
abstract = {BackgroundImage-based plant phenotyping has become a
powerful tool in unravelling genotype–environment
interactions. The utilization of image analysis and machine
learning have become paramount in extracting data stemming
from phenotyping experiments. Yet we rely on observer (a
human expert) input to perform the phenotyping process. We
assume such input to be a ‘gold-standard’ and use it to
evaluate software and algorithms and to train learning-based
algorithms. However, we should consider whether any
variability among experienced and non-experienced (including
plain citizens) observers exists. Here we design a study
that measures such variability in an annotation task of an
integer-quantifiable phenotype: the leaf count.ResultsWe
compare several experienced and non-experienced observers in
annotating leaf counts in images of Arabidopsis Thaliana to
measure intra- and inter-observer variability in a
controlled study using specially designed annotation tools
but also citizens using a distributed citizen-powered
web-based platform. In the controlled study observers
counted leaves by looking at top-view images, which were
taken with low and high resolution optics. We assessed
whether the utilization of tools specifically designed for
this task can help to reduce such variability. We found that
the presence of tools helps to reduce intra-observer
variability, and that although intra- and inter-observer
variability is present it does not have any effect on
longitudinal leaf count trend statistical assessments. We
compared the variability of citizen provided annotations
(from the web-based platform) and found that plain citizens
can provide statistically accurate leaf counts. We also
compared a recent machine-learning based leaf counting
algorithm and found that while close in performance it is
still not within inter-observer variability.ConclusionsWhile
expertise of the observer plays a role, if sufficient
statistical power is present, a collection of
non-experienced users and even citizens can be included in
image-based phenotyping annotation tasks as long they are
suitably designed. We hope with these findings that we can
re-evaluate the expectations that we have from automated
algorithms: as long as they perform within observer
variability they can be considered a suitable alternative.
In addition, we hope to invigorate an interest in
introducing suitably designed tasks on citizen powered
platforms not only to obtain useful information (for
research) but to help engage the public in this societal
important problem.},
cin = {IBG-2},
ddc = {580},
cid = {I:(DE-Juel1)IBG-2-20101118},
pnm = {582 - Plant Science (POF3-582) / 583 - Innovative
Synergisms (POF3-583)},
pid = {G:(DE-HGF)POF3-582 / G:(DE-HGF)POF3-583},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:29449872},
UT = {WOS:000425015500001},
doi = {10.1186/s13007-018-0278-7},
url = {https://juser.fz-juelich.de/record/843816},
}