Shack-Hartmann based wavefront and intensity sensing via U-Net

Feng-Chun Hsu; Chun-Yu Lin; Chia-Yuan Chang; Shean-Jen Chen

doi:10.1117/12.2620264

24 May 2022 Shack-Hartmann based wavefront and intensity sensing via U-Net

Feng-Chun Hsu, Chun-Yu Lin, Chia-Yuan Chang, Shean-Jen Chen

Proceedings Volume 12136, Unconventional Optical Imaging III; 121360A (2022) https://doi.org/10.1117/12.2620264
Event: SPIE Photonics Europe, 2022, Strasbourg, France

Abstract

Neural networks present a new approach for solving nonlinear problems and is widely applied in optical science. In this research, we integrate neural network with Shack-Hartmann wavefront sensor (SHWS), not only reconstruct the wavefront but also the intensity of beam profile. This network has the capability to obtain the beam wavefront information without calculating the slop of wavefront, which cost most of the time in traditional algorithm, and also grab the features of beam intensity distribution simultaneously. We also compare the result of reconstruction using single focal spot. The experimental results show that though SHWS pattern training result has slightly better root mean square (RMS), both the reconstructions have high accuracy in wavefront and beam profile.

Conference Presentation

Citation Download Citation

Feng-Chun Hsu, Chun-Yu Lin, Chia-Yuan Chang, and Shean-Jen Chen "Shack-Hartmann based wavefront and intensity sensing via U-Net", Proc. SPIE 12136, Unconventional Optical Imaging III, 121360A (24 May 2022); https://doi.org/10.1117/12.2620264

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