Binary Maps for Image Separation inIterative Neuronal Network Applications
Roman Lehmann, Stanislav Arnaudov, Markus Hoffmann, Wolfgang Karl
Kapitel/Beitrag aus dem Buch: Heizmann M. & Längle T. 2020. Forum Bildverarbeitung 2020.
Part of
Kapitel/Beitrag aus dem Buch: Heizmann M. & Längle T. 2020. Forum Bildverarbeitung 2020.
Generating a series of images is an important task in
various fields of scientific research, e. g. Computational fluid
dynamics (CFD). In the past years, solutions based on deep
neural networks gained importance. In these tasks, it’s often
necessary to declare regions of interest in the image. Furthermore,
the NN should only perform on these regions and the
rest should be ignored. With this paper, we propose an innovative
and easy method for implementing this behavior in the
field of CFD.
Lehmann, R et al. 2020. Binary Maps for Image Separation inIterative Neuronal Network Applications. In: Heizmann M. & Längle T (eds.), Forum Bildverarbeitung 2020. Karlsruhe: KIT Scientific Publishing. DOI: https://doi.org/10.58895/ksp/1000124383-29
This chapter distributed under the terms of the Creative Commons Attribution + ShareAlike 4.0 license. Copyright is retained by the author(s)
Dieses Buch ist Peer reviewed. Informationen dazu Hier finden Sie mehr Informationen zur wissenschaftlichen Qualitätssicherung der MAP-Publikationen.
Veröffentlicht am 25. November 2020