Translator Disclaimer
Paper
6 July 2018 Smart starting guesses from machine learning for phase retrieval
Author Affiliations +
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.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
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
PROCEEDINGS
7 PAGES


SHARE
Advertisement
Advertisement
Back to Top