Multiple-input deep neural network aberration correction for measurements in microfluidics through fluctuating phase boundaries

Lars Büttner; Zeyu Gao; Ping Yang; Clemens Bilsing; Jürgen W. Czarske

doi:10.1117/12.3028086

4 October 2024 Multiple-input deep neural network aberration correction for measurements in microfluidics through fluctuating phase boundaries

Lars Büttner, Zeyu Gao, Ping Yang, Clemens Bilsing, Jürgen W. Czarske

Author Affiliations +

Proceedings Volume PC13149, Unconventional Imaging, Sensing, and Adaptive Optics 2024; PC131490B (2024) https://doi.org/10.1117/12.3028086
Event: Optical Engineering + Applications, 2024, San Diego, California, United States

Abstract

Imaging-based particle localization and tracking measurements can be subject to significant measurement errors if the measurement is performed through a temporally varying air-water interface. This situation occurs in a huge variety of technical energy conversion processes like bubble formation in electrolysis, droplet formation in fuel cells, or film flows. An actuator-free approach for the correction of time-varying low-order aberrations is presented. It is based a multiple-input deep convolutional neural network that uses an additional wavefront sensor input. Application is demonstrated by means of a flow measurement through an open, oscillating water surface. We show that the measurement error of the flow velocity induced by the fluctuating aberrations can be reduced up to 82 % if the correction is applied. This actuator-free approach has a potential to correct distortions in real-time which are uncorrectable for traditional AO systems which are limited by the performance of available actuators.

Conference Presentation

Citation Download Citation

Lars Büttner, Zeyu Gao, Ping Yang, Clemens Bilsing, and Jürgen W. Czarske "Multiple-input deep neural network aberration correction for measurements in microfluidics through fluctuating phase boundaries", Proc. SPIE PC13149, Unconventional Imaging, Sensing, and Adaptive Optics 2024, PC131490B (4 October 2024); https://doi.org/10.1117/12.3028086

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