TY - JOUR
AU - Trampert, Patrick
AU - Rubinstein, Dmitri
AU - Boughorbel, Faysal
AU - Schlinkmann, Christian
AU - Luschkova, Maria
AU - Slusallek, Philipp
AU - Dahmen, Tim
AU - Sandfeld, Stefan
TI - Deep Neural Networks for Analysis of Microscopy Images—Synthetic Data Generation and Adaptive Sampling
JO - Crystals
VL - 11
IS - 3
SN - 2073-4352
CY - Basel
PB - MDPI
M1 - FZJ-2021-01587
SP - 258 -
PY - 2021
AB - The analysis of microscopy images has always been an important yet time consuming process in materials science. Convolutional Neural Networks (CNNs) have been very successfully used for a number of tasks, such as image segmentation. However, training a CNN requires a large amount of hand annotated data, which can be a problem for material science data. We present a procedure to generate synthetic data based on ad hoc parametric data modelling for enhancing generalization of trained neural network models. Especially for situations where it is not possible to gather a lot of data, such an approach is beneficial and may enable to train a neural network reasonably. Furthermore, we show that targeted data generation by adaptively sampling the parameter space of the generative models gives superior results compared to generating random data points.
LB - PUB:(DE-HGF)16
UR - <Go to ISI:>//WOS:000633604100001
DO - DOI:10.3390/cryst11030258
UR - https://juser.fz-juelich.de/record/891562
ER -