Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

3D Image Acquisition and Display: Technology, Perception and Applications 2025: introduction.

Applied optics·2026

Same author

Feature issue introduction: 3D image acquisition and display: technology, perception and applications.

Optics express·2026

Same author

Lensless variable magnification by 200 µm single-fiber ghost imaging.

Applied optics·2026

Same author

Single-pixel microscopy with enhanced lateral resolution.

Optics express·2025

Same author

Sub-diffraction ghost imaging with holographic pattern illumination.

Optics express·2025

Same author

Red-shifted excitation enhances the sensitivity of red genetically encoded Ca<sup>2+</sup> indicator and enables crosstalk-free two-photon holographic optophysiology.

Journal of biomedical optics·2025

Same journal

Multifunctional reconfigurable terahertz metasurface based on vanadium dioxide phase transition: achieving broadband absorption and efficient polarization conversion.

Applied optics·2026

Same journal

High-Q-factor electromagnetically induced transparency utilizing quasi-bound states in the continuum in an all-dielectric terahertz metasurface.

Applied optics·2026

Same journal

Automated stitching interferometry for high-precision metrology of X-ray mirrors.

Applied optics·2026

Same journal

Experimental demonstration of an approach to designing a metal-dielectric DBR resonant cavity structure.

Applied optics·2026

Same journal

High-precision wavefront reconstruction from a single-shot interferogram using a physics-driven hybrid feature calibration network.

Applied optics·2026

Same journal

Ultra-high-Q Fano resonance based on coupled topological corner states in Kagome photonic crystals.

Applied optics·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Aug 15, 2025

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Published on: July 3, 2021

Noise-robust deep learning ghost imaging using a non-overlapping pattern for defect position mapping.

Shoma Kataoka, Yasuhiro Mizutani, Tsutomu Uenohara

|January 6, 2023

Summary

This summary is machine-generated.

Non-overlapping illumination patterns enhance deep learning ghost imaging (DLGI) for defect detection. This method improves noise robustness and position accuracy without altering the convolutional neural network (CNN).

More Related Videos

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

Related Experiment Videos

Last Updated: Aug 15, 2025

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Published on: July 3, 2021

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

Area of Science:

Optics and photonics
Artificial intelligence
Materials science

Background:

Defect detection demands sensitive and robust inspection techniques.
Deep learning ghost imaging (DLGI) accelerates ghost imaging (GI) but reduces robustness.
Existing DLGI methods face challenges with noise sensitivity.

Purpose of the Study:

To enhance the noise robustness of deep learning ghost imaging (DLGI).
To improve defect detection accuracy in noisy environments using DLGI.
To evaluate the impact of non-overlapping illumination patterns on DLGI performance.

Main Methods:

Utilizing non-overlapping illumination patterns generated via binary notation.
Applying these patterns to the input data of a convolutional neural network (CNN).
Evaluating the robustness and position accuracy of DLGI under noisy conditions.

Main Results:

Non-overlapping patterns significantly improve DLGI's noise robustness.
Position accuracy in defect detection is enhanced by up to 51%.
The convolutional neural network (CNN) architecture remains unmodified.

Conclusions:

Non-overlapping illumination patterns offer a viable strategy to boost DLGI robustness.
This approach enables more accurate defect detection in challenging, noisy environments.
DLGI can be made more reliable for practical inspection tasks without complex network modifications.