Smart starting guesses from machine learning for phase retrieval

Scott W. Paine; James R. Fienup

doi:10.1117/12.2307858

6 July 2018 Smart starting guesses from machine learning for phase retrieval

Scott W. Paine, James R. Fienup

Proceedings Volume 10698, Space Telescopes and Instrumentation 2018: Optical, Infrared, and Millimeter Wave; 106985W (2018) https://doi.org/10.1117/12.2307858
Event: SPIE Astronomical Telescopes + Instrumentation, 2018, Austin, Texas, United States

Abstract

Image-based wavefront sensing uses a physical model to simulate a point-spread function (PSF) that attempts to match measured data. Nonlinear optimization is used to update parameters corresponding to the wavefront. If the starting guess for the wavefront is too far from the true solution, these nonlinear optimization techniques are unlikely to converge. We trained a convolutional neural network (CNN) based on Google’s Inception v3 architecture¹ to predict Zernike coefficients from simulated images of PSFs with simulated noise added. These coefficients were used as starting guesses for nonlinear optimization techniques. We performed Monte Carlo analysis to compare these predicted coefficients to 30 random starting guesses for total root-mean-square (RMS) wavefront errors (WFE) ranging from 0.25 waves to 4.0 waves. We found that our CNN’s predictions were more likely to converge than the random starting guesses for RMS WFE larger than 0.5 waves.

Citation Download Citation

Scott W. Paine and James R. Fienup "Smart starting guesses from machine learning for phase retrieval", Proc. SPIE 10698, Space Telescopes and Instrumentation 2018: Optical, Infrared, and Millimeter Wave, 106985W (6 July 2018); https://doi.org/10.1117/12.2307858

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