Deep-learning-based high-resolution recognition of rotating interference images in vortex beam interferometry

Xibo Sun; Yilin Yao; Yuanchao Geng; Yu Xie

doi:10.1117/12.3014898

22 December 2023 Deep-learning-based high-resolution recognition of rotating interference images in vortex beam interferometry

Xibo Sun, Yilin Yao, Yuanchao Geng, Yu Xie

Author Affiliations +

Proceedings Volume 12974, Fifth International Symposium on High Power Laser Science and Engineering (HPLSE 2023); 129740B (2023) https://doi.org/10.1117/12.3014898
Event: Fifth International Symposium on High Power Laser Science and Engineering, 2023, Suzhou, China

Abstract

The vortex beam can improve the resolution of the interferometry by converting the continuous phase shift into the rotation angle of the interference image. This research focuses on the high-resolution recognition of rotating interference images in the vortex beam interferometry. The present paper explores deep-learning technology by establishing a residual convolutional neural network to recognize the rotation angles of interference profiles. After well trained, the proposed network model is able to achieve an image rotation recognition resolution of 9.19 milli-radians, and the corresponding displacement measurement resolution is 0.92 nm. Due to the competitive resolution, the proposed method shows great potential in precise measurements.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Xibo Sun, Yilin Yao, Yuanchao Geng, and Yu Xie "Deep-learning-based high-resolution recognition of rotating interference images in vortex beam interferometry", Proc. SPIE 12974, Fifth International Symposium on High Power Laser Science and Engineering (HPLSE 2023), 129740B (22 December 2023); https://doi.org/10.1117/12.3014898

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available