Macroscopic Fourier Ptychographic Imaging Based on Deep Learning

Fourier Ptychography (FP) is a powerful computational imaging technique that enables high-resolution, wide-field imaging by synthesizing apertures and leveraging coherent diffraction. However, the application of FP in long-distance imaging has been limited due to challenges such as noise and optical...

Full description

Saved in:
Bibliographic Details
Main Authors: Junyuan Liu, Wei Sun, Fangxun Wu, Haoming Shan, Xiangsheng Xie
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Photonics
Subjects:
Online Access:https://www.mdpi.com/2304-6732/12/2/170
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850082317510377472
author Junyuan Liu
Wei Sun
Fangxun Wu
Haoming Shan
Xiangsheng Xie
author_facet Junyuan Liu
Wei Sun
Fangxun Wu
Haoming Shan
Xiangsheng Xie
author_sort Junyuan Liu
collection DOAJ
description Fourier Ptychography (FP) is a powerful computational imaging technique that enables high-resolution, wide-field imaging by synthesizing apertures and leveraging coherent diffraction. However, the application of FP in long-distance imaging has been limited due to challenges such as noise and optical aberrations. This study introduces deep learning methods following macroscopic FP to further enhance image quality. Specifically, we employ super-resolution convolutional neural networks and very deep super-resolution, incorporating residual learning and residual neural network architectures to optimize network performance. These techniques significantly improve the resolution and clarity of FP images. Experiments with real-world film samples demonstrate the effectiveness of the proposed methods in practical applications. This research highlights the potential of deep learning to advance computational imaging techniques like FP, paving the way for improved long-distance imaging capabilities.
format Article
id doaj-art-d468b200230842ebaf982e6fb6e6658a
institution DOAJ
issn 2304-6732
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Photonics
spelling doaj-art-d468b200230842ebaf982e6fb6e6658a2025-08-20T02:44:32ZengMDPI AGPhotonics2304-67322025-02-0112217010.3390/photonics12020170Macroscopic Fourier Ptychographic Imaging Based on Deep LearningJunyuan Liu0Wei Sun1Fangxun Wu2Haoming Shan3Xiangsheng Xie4Department of Physics, College of Science, Shantou University, Shantou 515063, ChinaDepartment of Physics, College of Science, Shantou University, Shantou 515063, ChinaDepartment of Physics, College of Science, Shantou University, Shantou 515063, ChinaDepartment of Physics, College of Science, Shantou University, Shantou 515063, ChinaDepartment of Physics, College of Science, Shantou University, Shantou 515063, ChinaFourier Ptychography (FP) is a powerful computational imaging technique that enables high-resolution, wide-field imaging by synthesizing apertures and leveraging coherent diffraction. However, the application of FP in long-distance imaging has been limited due to challenges such as noise and optical aberrations. This study introduces deep learning methods following macroscopic FP to further enhance image quality. Specifically, we employ super-resolution convolutional neural networks and very deep super-resolution, incorporating residual learning and residual neural network architectures to optimize network performance. These techniques significantly improve the resolution and clarity of FP images. Experiments with real-world film samples demonstrate the effectiveness of the proposed methods in practical applications. This research highlights the potential of deep learning to advance computational imaging techniques like FP, paving the way for improved long-distance imaging capabilities.https://www.mdpi.com/2304-6732/12/2/170FPSRCNNVDSRresidual learningResNet
spellingShingle Junyuan Liu
Wei Sun
Fangxun Wu
Haoming Shan
Xiangsheng Xie
Macroscopic Fourier Ptychographic Imaging Based on Deep Learning
Photonics
FP
SRCNN
VDSR
residual learning
ResNet
title Macroscopic Fourier Ptychographic Imaging Based on Deep Learning
title_full Macroscopic Fourier Ptychographic Imaging Based on Deep Learning
title_fullStr Macroscopic Fourier Ptychographic Imaging Based on Deep Learning
title_full_unstemmed Macroscopic Fourier Ptychographic Imaging Based on Deep Learning
title_short Macroscopic Fourier Ptychographic Imaging Based on Deep Learning
title_sort macroscopic fourier ptychographic imaging based on deep learning
topic FP
SRCNN
VDSR
residual learning
ResNet
url https://www.mdpi.com/2304-6732/12/2/170
work_keys_str_mv AT junyuanliu macroscopicfourierptychographicimagingbasedondeeplearning
AT weisun macroscopicfourierptychographicimagingbasedondeeplearning
AT fangxunwu macroscopicfourierptychographicimagingbasedondeeplearning
AT haomingshan macroscopicfourierptychographicimagingbasedondeeplearning
AT xiangshengxie macroscopicfourierptychographicimagingbasedondeeplearning