Digital Hologram Denoising Using Conditional Generative Adversarial Networks

Siddharth Rawat; Anna Wang

doi:10.1364/dh.2021.dm5e.6

ScienceGate Book Chapters

JOURNAL ARTICLE

Digital Hologram Denoising Using Conditional Generative Adversarial Networks

Siddharth Rawat Anna Wang

Year: 2021 Journal: OSA Imaging and Applied Optics Congress 2021 (3D, COSI, DH, ISA, pcAOP) Pages: DM5E.6-DM5E.6

DOI: 10.1364/dh.2021.dm5e.6

Get Full-Text PDF Get Analytical Report

Abstract

Accurate feature extraction from digitally acquired in-line and off-axis holograms using analytical methods is challenging in the presence of noise. We present a strategy to overcome this limitation by using conditional generative adversarial networks (cGANs).

Keywords:

Computer science Holography Generative grammar Artificial intelligence Noise reduction Adversarial system Feature extraction Noise (video) Pattern recognition (psychology) Feature (linguistics) Generative adversarial network Computer vision Image (mathematics) Optics

Metrics

Cited By

0.00

FWCI (Field Weighted Citation Impact)

Refs

0.34

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Topics

Digital Holography and Microscopy

Physical Sciences → Physics and Astronomy → Atomic and Molecular Physics, and Optics

Image Processing Techniques and Applications

Physical Sciences → Engineering → Media Technology

Advanced Optical Imaging Technologies

Physical Sciences → Engineering → Media Technology

Digital Hologram Denoising Using Conditional Generative Adversarial Networks

Abstract

Metrics

Topics

Related Documents

Wireless Signal Denoising Using Conditional Generative Adversarial Networks

Ultrasonic imaging using conditional generative adversarial networks

Clustering Using Conditional Generative Adversarial Networks (cGANs)

Gesture Recognition using Conditional Generative Adversarial Networks

Imaging Domain Seismic Denoising Based on Conditional Generative Adversarial Networks (CGANs)