Loading [MathJax]/extensions/tex2jax.js

Super-resolution for 2.5D height data of microstructured surfaces using the vdsr network

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschung

Autorschaft

Details

OriginalspracheEnglisch
Titel des SammelwerksEOS Annual Meeting (EOSAM 2020)
Herausgeber/-innenH. Michinel, M. F. Costa, O. Fraazao
Herausgeber (Verlag)EDP Sciences
Seitenumfang2
PublikationsstatusVeröffentlicht - 20 Aug. 2020

Publikationsreihe

NameEPJ Web of Conferences
Herausgeber (Verlag)EDP Sciences
Band238
ISSN (Print)2101-6275
ISSN (elektronisch)2100-014X

Abstract

In this work super-resolution imaging is used to enhance 2.5D height data of thermal sprayed Al2O3 ceramics with stochastically microstructured surfaces. The data is obtained by means of a confocal laser scanning microscope. By implementing and training a Very Deep Super-Resolution neural network to generate residual images an improvement of the peak signal-to-noise ratio and structural similarity index can be observed when compared to classic interpolation methods.

Zitieren

Super-resolution for 2.5D height data of microstructured surfaces using the vdsr network. / Siemens, Stefan; Kästner, Markus; Reithmeier, Eduard.
EOS Annual Meeting (EOSAM 2020). Hrsg. / H. Michinel; M. F. Costa; O. Fraazao. EDP Sciences, 2020. (EPJ Web of Conferences; Band 238).

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschung

Siemens, S, Kästner, M & Reithmeier, E 2020, Super-resolution for 2.5D height data of microstructured surfaces using the vdsr network. in H Michinel, MF Costa & O Fraazao (Hrsg.), EOS Annual Meeting (EOSAM 2020). EPJ Web of Conferences, Bd. 238, EDP Sciences. https://doi.org/10.1051/epjconf/202023806014
Siemens, S., Kästner, M., & Reithmeier, E. (2020). Super-resolution for 2.5D height data of microstructured surfaces using the vdsr network. In H. Michinel, M. F. Costa, & O. Fraazao (Hrsg.), EOS Annual Meeting (EOSAM 2020) (EPJ Web of Conferences; Band 238). EDP Sciences. https://doi.org/10.1051/epjconf/202023806014
Siemens S, Kästner M, Reithmeier E. Super-resolution for 2.5D height data of microstructured surfaces using the vdsr network. in Michinel H, Costa MF, Fraazao O, Hrsg., EOS Annual Meeting (EOSAM 2020). EDP Sciences. 2020. (EPJ Web of Conferences). doi: 10.1051/epjconf/202023806014
Siemens, Stefan ; Kästner, Markus ; Reithmeier, Eduard. / Super-resolution for 2.5D height data of microstructured surfaces using the vdsr network. EOS Annual Meeting (EOSAM 2020). Hrsg. / H. Michinel ; M. F. Costa ; O. Fraazao. EDP Sciences, 2020. (EPJ Web of Conferences).
Download
@inproceedings{17d99c0a9f6e4770866200b4ff668bf5,
title = "Super-resolution for 2.5D height data of microstructured surfaces using the vdsr network",
abstract = "In this work super-resolution imaging is used to enhance 2.5D height data of thermal sprayed Al2O3 ceramics with stochastically microstructured surfaces. The data is obtained by means of a confocal laser scanning microscope. By implementing and training a Very Deep Super-Resolution neural network to generate residual images an improvement of the peak signal-to-noise ratio and structural similarity index can be observed when compared to classic interpolation methods.",
author = "Stefan Siemens and Markus K{\"a}stner and Eduard Reithmeier",
year = "2020",
month = aug,
day = "20",
doi = "10.1051/epjconf/202023806014",
language = "English",
series = "EPJ Web of Conferences",
publisher = "EDP Sciences",
editor = "H. Michinel and Costa, {M. F.} and O. Fraazao",
booktitle = "EOS Annual Meeting (EOSAM 2020)",
address = "France",

}

Download

TY - GEN

T1 - Super-resolution for 2.5D height data of microstructured surfaces using the vdsr network

AU - Siemens, Stefan

AU - Kästner, Markus

AU - Reithmeier, Eduard

PY - 2020/8/20

Y1 - 2020/8/20

N2 - In this work super-resolution imaging is used to enhance 2.5D height data of thermal sprayed Al2O3 ceramics with stochastically microstructured surfaces. The data is obtained by means of a confocal laser scanning microscope. By implementing and training a Very Deep Super-Resolution neural network to generate residual images an improvement of the peak signal-to-noise ratio and structural similarity index can be observed when compared to classic interpolation methods.

AB - In this work super-resolution imaging is used to enhance 2.5D height data of thermal sprayed Al2O3 ceramics with stochastically microstructured surfaces. The data is obtained by means of a confocal laser scanning microscope. By implementing and training a Very Deep Super-Resolution neural network to generate residual images an improvement of the peak signal-to-noise ratio and structural similarity index can be observed when compared to classic interpolation methods.

U2 - 10.1051/epjconf/202023806014

DO - 10.1051/epjconf/202023806014

M3 - Conference contribution

T3 - EPJ Web of Conferences

BT - EOS Annual Meeting (EOSAM 2020)

A2 - Michinel, H.

A2 - Costa, M. F.

A2 - Fraazao, O.

PB - EDP Sciences

ER -

Von denselben Autoren