Kapitel/Beitrag aus dem Buch: Längle T. & Heizmann M. 2022. Forum Bildverarbeitung 2022.
In this work, we propose a physics-enhanced two-toone Y-neural network (two inputs and one output) for phase retrieval of complex wavefronts from two diffraction patterns. The learnable parameters of the Y-net are optimized by minimizing a hybrid loss function, which evaluates the root-mean-square error and normalized Pearson correlated coefficient on the two diffraction planes. An angular spectrum method network is designed for self-supervised training on the Y-net. Amplitudes and phases of wavefronts diffracted by a USAF-1951 resolution target, a phase grating of 200 lp/mm, and a skeletal muscle cell were retrieved using a Y-net with 100 learning iterations. Fast reconstructions could be realized without constraints or a priori knowledge of the samples.
Li, R et al. 2022. Physics enhanced neural network for phase imaging using two axially displaced diffraction patterns. In: Längle T. & Heizmann M (eds.), Forum Bildverarbeitung 2022. Karlsruhe: KIT Scientific Publishing. DOI: https://doi.org/10.58895/ksp/1000150865-2
This chapter distributed under the terms of the Creative Commons Attribution + ShareAlike 4.0 license. Copyright is retained by the author(s)
Dieses Buch ist Peer reviewed. Informationen dazu Hier finden Sie mehr Informationen zur wissenschaftlichen Qualitätssicherung der MAP-Publikationen.
Veröffentlicht am 25. November 2022