% 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{Govind:1021215,
author = {Govind, Kishan and Oliveros, Daniela and Dlouhy, Antonin
and Legros, Marc and Sandfeld, Stefan},
title = {{D}eep learning of crystalline defects from {TEM} images: a
solution for the problem of ‘never enough training
data’},
journal = {Machine learning: science and technology},
volume = {5},
number = {1},
issn = {2632-2153},
address = {Bristol},
publisher = {IOP Publishing},
reportid = {FZJ-2024-00656},
pages = {015006 -},
year = {2024},
abstract = {Crystalline defects, such as line-like dislocations, play
an important role for the performance and reliability of
many metallic devices. Their interaction and evolution still
poses a multitude of open questions to materials science and
materials physics. In-situ transmission electron microscopy
(TEM) experiments can provide important insights into how
dislocations behave and move. The analysis of individual
video frames from such experiments can provide useful
insights but is limited by the capabilities of automated
identification, digitization, and quantitative extraction of
the dislocations as curved objects. The vast amount of data
also makes manual annotation very time consuming, thereby
limiting the use of deep learning (DL)-based, automated
image analysis and segmentation of the dislocation
microstructure. In this work, a parametric model for
generating synthetic training data for segmentation of
dislocations is developed. Even though domain scientists
might dismiss synthetic images as artificial, our findings
show that they can result in superior performance.
Additionally, we propose an enhanced DL method optimized for
segmenting overlapping or intersecting dislocation lines.
Upon testing this framework on four distinct real datasets,
we find that a model trained only on synthetic training data
can also yield high-quality results on real images–even
more so if the model is further fine-tuned on a few real
images. Our approach demonstrates the potential of synthetic
data in overcoming the limitations of manual annotation of
TEM image data of dislocation microstructure, paving the way
for more efficient and accurate analysis of dislocation
microstructures. Last but not least, segmenting such thin,
curvilinear structures is a task that is ubiquitous in many
fields, which makes our method a potential candidate for
other applications as well.},
cin = {IAS-9},
ddc = {621.3},
cid = {I:(DE-Juel1)IAS-9-20201008},
pnm = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
(SDLs) and Research Groups (POF4-511)},
pid = {G:(DE-HGF)POF4-5111},
typ = {PUB:(DE-HGF)16},
UT = {WOS:001142818000001},
doi = {10.1088/2632-2153/ad1a4e},
url = {https://juser.fz-juelich.de/record/1021215},
}