%0 Journal Article
%A Trampert, Patrick
%A Rubinstein, Dmitri
%A Boughorbel, Faysal
%A Schlinkmann, Christian
%A Luschkova, Maria
%A Slusallek, Philipp
%A Dahmen, Tim
%A Sandfeld, Stefan
%T Deep Neural Networks for Analysis of Microscopy Images—Synthetic Data Generation and Adaptive Sampling
%J Crystals
%V 11
%N 3
%@ 2073-4352
%C Basel
%I MDPI
%M FZJ-2021-01587
%P 258 -
%D 2021
%X 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.
%F PUB:(DE-HGF)16
%9 Journal Article
%U <Go to ISI:>//WOS:000633604100001
%R 10.3390/cryst11030258
%U https://juser.fz-juelich.de/record/891562