公开(公告)号：US20240354907A1

公开(公告)日：2024-10-24

申请号：US18637317

申请日：2024-04-16

Applicant: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA

Inventor： Aydogan Ozcan ,  Hanlong Chen ,  Luzhe Huang

IPC: G06T5/60 ,  G03H1/00 ,  G03H1/26 ,  G06T5/50 ,  G06T5/73

CPC classification number: G06T5/60 ,  G03H1/0005 ,  G03H1/26 ,  G06T5/50 ,  G06T5/73 ,  G03H2001/005 ,  G03H2210/55 ,  G03H2226/02 ,  G03H2227/03 ,  G06T2207/10056 ,  G06T2207/20021 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30024

Abstract: A deep learning framework, termed Fourier Imager Network (FIN) is disclosed that can perform end-to-end phase recovery and image reconstruction from raw holograms of new types of samples, exhibiting success in external generalization. The FIN architecture is based on spatial Fourier transform modules with the deep neural network that process the spatial frequencies of its inputs using learnable filters and a global receptive field. FIN exhibits superior generalization to new types of samples, while also being much faster in its image inference speed, completing the hologram reconstruction task in ˜0.04 s per 1 mm2 of the sample area. Beyond holographic microscopy and quantitative phase imaging applications, FIN and the underlying neural network architecture may open up various new opportunities to design broadly generalizable deep learning models in computational imaging and machine vision fields.