Details
| Originalsprache | Englisch |
|---|---|
| Seiten | 282-283 |
| Publikationsstatus | Veröffentlicht - 2023 |
| Veranstaltung | Sensor and Measurement Science International - Nürnberg, Deutschland Dauer: 8 Mai 2023 → 11 Mai 2023 Konferenznummer: 2023 https://www.smsi-conference.com/ |
Konferenz
| Konferenz | Sensor and Measurement Science International |
|---|---|
| Kurztitel | SMSI |
| Land/Gebiet | Deutschland |
| Ort | Nürnberg |
| Zeitraum | 8 Mai 2023 → 11 Mai 2023 |
| Internetadresse |
Abstract
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
2023. 282-283 Postersitzung präsentiert bei Sensor and Measurement Science International, Nürnberg, Deutschland.
Publikation: Konferenzbeitrag › Poster › Forschung
}
TY - CONF
T1 - Non-Overlap Image Registration
AU - Siemens, Stefan
AU - Kästner, Markus
AU - Reithmeier, Eduard
N1 - Conference code: 2023
PY - 2023
Y1 - 2023
N2 - This work aims to predict the relative position of non-overlapping image pairs consisting of a moving and a fixed image. For this purpose, a modified VGG16 convolutional neural network is proposed. The network is trained on a large dataset with microtopographic measurement data of different materials and processing methods. The proposed method shows a high prediction accuracy on the test data and the potential for developing non-overlap registration algorithms.
AB - This work aims to predict the relative position of non-overlapping image pairs consisting of a moving and a fixed image. For this purpose, a modified VGG16 convolutional neural network is proposed. The network is trained on a large dataset with microtopographic measurement data of different materials and processing methods. The proposed method shows a high prediction accuracy on the test data and the potential for developing non-overlap registration algorithms.
U2 - 10.5162/smsi2023/p01
DO - 10.5162/smsi2023/p01
M3 - Poster
SP - 282
EP - 283
T2 - Sensor and Measurement Science International
Y2 - 8 May 2023 through 11 May 2023
ER -