.png){kind=icon}
Return
Simulation-Training-Based Deep Learning Approach to Microscopic Ghost Imaging
.png){kind=icon}
OA
AI
DOI：10.1002/adpr.202400052.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Herein, deep learning-ghost imaging (DLGI) based on a digital micromirror device is realized to avoid the difficulties of a charge-coupled device (CCD) scientific camera being unable to obtain the sample images in extremely weak illumination conditions and to solve the problem of the inverse relationship between imaging quality and imaging time in practical applications. Deep learning for computational ghost imaging typically requires the collection of a large set of labeled experimental data to train a neural network. Herein, we demonstrate that a practically usable neural network can be prepared based on the simulation results. The acquisition results of the CCD scientific camera and the simulation results with low sampling are used as the training set (1000 observations) and we can complete the data acquisition process within one hour. The results show that the proposed DLGI method can be used to significantly improve the quality of the reconstructed images when the sampling rate is 60%. This method also reduces the imaging time and the memory usage, while simultaneously improving the imaging quality. The imaging results of the proposed DLGI method have great significance for application in clinical diagnosis. Herein, deep learning-ghost imaging based on a digital micromirror device is realized to avoid the difficulties of a Charge-coupled device scientific camera being unable to obtain the sample images in extremely weak illumination conditions. This method also reduces the imaging time and the memory usage, while simultaneously improving the imaging quality.image (c) 2024 WILEY-VCH GmbH
Keywords:
deep learning
ghost imaging
microscopy imaging
simulation training
Journal
IF:
18.8
Papers:
981
Citations:
3.6K
Organization
View more organizations
Cited Papers
SeedQuant: a deep learning-based tool for assessing stimulant and inhibitor activity on root parasitic seeds.png)
PLANT PHYSIOLOGY
OAAI
PLANT PHYSIOLOGYIF6.9
OAAIShareSaveShareSaveShareSaveShareSaveDual-objective STORM reveals three-dimensional filament organization in the actin cytoskeletonNATURE METHODSOAAI
NATURE METHODSIF32.1
OAAIShareSaveShareSave View more