Robust sensorless wavefront sensing via neural network in a single-shot

Yuanlong Zhang; Hao Xie; Qionghai Dai

doi:10.1117/12.2545158

17 February 2020 Robust sensorless wavefront sensing via neural network in a single-shot

Yuanlong Zhang, Hao Xie, Qionghai Dai

Proceedings Volume 11248, Adaptive Optics and Wavefront Control for Biological Systems VI; 112480E (2020) https://doi.org/10.1117/12.2545158
Event: SPIE BiOS, 2020, San Francisco, California, United States

Abstract

Sensorless adaptive optics (AO) has been widely used in optical microscopy to improve imaging quality in scattering tissue without additional wavefront sensing devices. The traditional image metric-based sensorless AO method requires multiple frames to assess aberrated wavefront, which is time consuming and even inaccurate when the aberration becomes large due to distortion mode crosstalk. Here we propose a neural network based wavefront sensing method which can accurately predict wavefront distortions across different aberration scales in a single-shot. Compared to the traditional method, the neural network approach reduces the prediction time by over one thousand folds. We validate the superior performances of neural network-based approach in both accuracy and speed through numerical simulations.

Citation Download Citation

Yuanlong Zhang, Hao Xie, and Qionghai Dai "Robust sensorless wavefront sensing via neural network in a single-shot", Proc. SPIE 11248, Adaptive Optics and Wavefront Control for Biological Systems VI, 112480E (17 February 2020); https://doi.org/10.1117/12.2545158

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