Journal Article

FZJ-2021-01587

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Deep Neural Networks for Analysis of Microscopy Images—Synthetic Data Generation and Adaptive Sampling

Trampert, P. ; Rubinstein, D. ; Boughorbel, F. ; Schlinkmann, C. ; Luschkova, M. ; Slusallek, P. ; Dahmen, T. ; Sandfeld, S. (Corresponding author)FZJ*

2021
MDPI Basel

This record in other databases:    

Please use a persistent id in citations: http://hdl.handle.net/2128/33772  doi:10.3390/cryst11030258

Abstract: 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.

---

Contributing Institute(s):

1. Materials Data Science and Informatics (IAS-9)

Research Program(s):

1. 5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511) (POF4-511)
2. MuDiLingo - A Multiscale Dislocation Language for Data-Driven Materials Science (759419) (759419)

Appears in the scientific report 2022

---

Database coverage:
; ; ; ; Article Processing Charges ; Clarivate Analytics Master Journal List ; Current Contents - Physical, Chemical and Earth Sciences ; DOAJ Seal ; Essential Science Indicators ; Fees ; IF < 5 ; JCR ; SCOPUS ; Science Citation Index Expanded ; Web of Science Core Collection

---