Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

Hyperspectral LSFM with DMD-only shaping and neural network reconstruction.

Optics express·2025
Same author

Hedgehog signalling in solitary motile cilia: detection and role of hedgehog factors in sperm functions and in vitro fertilization.

Reproduction (Cambridge, England)·2025
Same author

Human cortical bone intrinsic permeability distribution based on 3D canalicular morphology.

Bone·2025
Same author

Enhancing fluorescence correlation spectroscopy with machine learning to infer anomalous molecular motion.

Biophysical journal·2025
Same author

Cell quantification at the osteochondral interface from synchrotron radiation phase contrast micro-computed tomography images using a deep learning approach.

Scientific reports·2024
Same author

3D quantification of the lacunocanalicular network on human femoral diaphysis through synchrotron radiation-based nanoCT.

Journal of structural biology·2024
Same journal

Denoising algorithm of Φ-OTDR systems based on adaptive fractional wavelet transform denoising.

Optics express·2026
Same journal

Millisecond photon-to-photon latency and high-speed volumetric projection system for optogenetics.

Optics express·2026
Same journal

Polarization-encoded coaxial structured light for high-precision 3D surface profilometry.

Optics express·2026
Same journal

Discrete freeform optical design based on collaborative optimization of point cloud and local normals.

Optics express·2026
Same journal

Ultrafast ghost imaging with 25 GHz speckle switching and wavelength-division multiplexing.

Optics express·2026
Same journal

Atomic vapor cells fabricated by femtosecond laser welding of standard-optical-quality glass.

Optics express·2026
See all related articles

Related Experiment Video

Updated: Nov 1, 2025

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
12:27

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

7.1K

Single-pixel image reconstruction from experimental data using neural networks.

Antonio Lorente Mur, Pierre Leclerc, Françoise Peyrin

    Optics Express
    |June 22, 2021
    PubMed
    Summary
    This summary is machine-generated.

    Deep neural networks reconstruct high-quality images in real time from single-pixel camera data. This method effectively handles mixed Poisson-Gaussian noise, improving image signal-to-noise ratios for computational optics applications.

    More Related Videos

    Author Spotlight: Deciphering Neural Circuit Formation from Two-Photon Microscopy and Single Neuron Imaging
    06:18

    Author Spotlight: Deciphering Neural Circuit Formation from Two-Photon Microscopy and Single Neuron Imaging

    Published on: November 21, 2023

    1.0K
    Photodiode-Based Optical Imaging for Recording Network Dynamics with Single-Neuron Resolution in Non-Transgenic Invertebrates
    10:18

    Photodiode-Based Optical Imaging for Recording Network Dynamics with Single-Neuron Resolution in Non-Transgenic Invertebrates

    Published on: July 9, 2020

    3.1K

    Related Experiment Videos

    Last Updated: Nov 1, 2025

    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
    12:27

    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

    Published on: February 15, 2017

    7.1K
    Author Spotlight: Deciphering Neural Circuit Formation from Two-Photon Microscopy and Single Neuron Imaging
    06:18

    Author Spotlight: Deciphering Neural Circuit Formation from Two-Photon Microscopy and Single Neuron Imaging

    Published on: November 21, 2023

    1.0K
    Photodiode-Based Optical Imaging for Recording Network Dynamics with Single-Neuron Resolution in Non-Transgenic Invertebrates
    10:18

    Photodiode-Based Optical Imaging for Recording Network Dynamics with Single-Neuron Resolution in Non-Transgenic Invertebrates

    Published on: July 9, 2020

    3.1K

    Area of Science:

    • Computational optics
    • Image processing
    • Deep learning

    Background:

    • Single-pixel cameras offer unique advantages for applications like hyper-spectral imaging.
    • Reconstructing images from limited measurements is a key challenge in computational imaging.
    • Existing methods struggle with noise, particularly mixed Poisson-Gaussian noise common in experimental setups.

    Purpose of the Study:

    • To develop a deep neural network framework for real-time, high-quality image reconstruction from single-pixel camera measurements.
    • To address and mitigate the impact of mixed Poisson-Gaussian noise during image reconstruction.
    • To create a robust training framework capable of handling varying noise levels in experimental data.

    Main Methods:

    • A deep neural network architecture was proposed, with the first layer implementing Tikhonov regularization to map measurement data to the image domain.
    • A novel training framework was developed, incorporating image intensity estimation, experimental parameter estimation, and a normalization scheme for noise level adaptation.
    • The network was trained and tested using both simulated data and experimental acquisitions under various noise conditions.

    Main Results:

    • The proposed deep neural network approach successfully reconstructed high-quality images in real time.
    • Significant improvements in peak signal-to-noise ratios (PSNR) were achieved, even with noise levels not explicitly seen during training.
    • The method demonstrated robustness across a range of noise levels, outperforming conventional techniques.

    Conclusions:

    • Deep neural networks, combined with Tikhonov regularization, provide an effective solution for real-time image reconstruction from single-pixel camera data.
    • The developed training framework enhances robustness to noise, making it suitable for real-world experimental conditions.
    • This approach has broad applicability in computational optics and can be adapted for other related problems.