Convolutional Neural Network (CNN) vs Vision Transformer (ViT) for Digital Holography
In: 2022 2nd International Conference on Computer, Control and Robotics (ICCCR) ; International Conference on Computer, 2022
Online
Konferenz
Zugriff:
International audience ; In Digital Holography (DH), it is crucial to extract the object distance from a hologram in order to reconstruct its amplitude and phase. This step is called auto-focusing and it is conventionally solved by first reconstructing a stack of images and then by sharpening each reconstructed image using a focus metric such as entropy or variance. The distance corresponding to the sharpest image is considered the focal position. This approach, while effective, is computationally demanding and time-consuming. In this paper, the determination of the distance is performed by Deep Learning (DL). Two deep learning (DL) achitectures are compared: Convolutional Neural Network (CNN) and Vision transformer (ViT). ViT and CNN are used to cope with the problem of auto-focusing as a classification problem. Compared to a first attempt [1] in which the distance between two consecutive classes was 100μm, our proposal allows us to drastically reduce this distance to 1μm. Moreover, ViT reaches similar accuracy and is more robust than CNN.
Titel: |
Convolutional Neural Network (CNN) vs Vision Transformer (ViT) for Digital Holography
|
---|---|
Autor/in / Beteiligte Person: | Cuenat, Stéphane ; Couturier, Raphael ; Franche-Comté Électronique Mécanique, Thermique et Optique - Sciences et Technologies (UMR 6174) (FEMTO-ST) ; Université de Technologie de Belfort-Montbeliard (UTBM)-Ecole Nationale Supérieure de Mécanique et des Microtechniques (ENSMM)-Centre National de la Recherche Scientifique (CNRS)-Université de Franche-Comté (UFC) ; Université Bourgogne Franche-Comté COMUE (UBFC)-Université Bourgogne Franche-Comté COMUE (UBFC) |
Link: | |
Zeitschrift: | 2022 2nd International Conference on Computer, Control and Robotics (ICCCR) ; International Conference on Computer, 2022 |
Veröffentlichung: | HAL CCSD, 2022 |
Medientyp: | Konferenz |
DOI: | 10.1109/ICCCR54399.2022.9790134 |
Schlagwort: |
|
Sonstiges: |
|