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 Experiment Video

Updated: Jun 7, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Photon-limited image classification with a feedforward neural network.

L A Saaf, G M Morris

    Applied Optics
    |November 6, 2010
    PubMed
    Summary
    This summary is machine-generated.

    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

    TBX18 overexpression enhances pacemaker function in a rat subsidiary atrial pacemaker model of sick sinus syndrome.

    The Journal of physiology·2018
    Same author

    Secretory cells in the clitellar epithelium of Eisenia foetida (Annelida, Oligochaeta): A histochemical and ultrastructural study.

    Journal of morphology·2018
    Same author

    Nature of weak magnetism in SrTiO3/LaAlO3 multilayers.

    Physical review letters·2013
    Same author

    Dr Pugh: a poisoner?

    Anaesthesia and intensive care·2012
    Same author

    Enhancement of the radiation response of EMT-6 tumours by a copper octabromotetracarboranylphenylporphyrin.

    The British journal of radiology·2011
    Same author

    The radiobiological principles of boron neutron capture therapy: a critical review.

    Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine·2011
    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

    This study applies neural networks to classify photon-limited images. The developed method accurately predicts classification probability, validated by experiments with printed characters.

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Image Processing

    Background:

    • Photon-limited imaging presents challenges for accurate image classification.
    • Traditional methods struggle with noise and low signal-to-noise ratios inherent in such images.
    • Neural networks offer a promising approach for complex pattern recognition tasks.

    Purpose of the Study:

    • To apply a feedforward neural network for classifying photon-limited images.
    • To develop a method for calculating the probability of correct image classification.
    • To validate the neural network's performance using experimental photon-limited image data.

    Main Methods:

    • Utilized a three-level feedforward neural network architecture.
    • Trained the network using the backpropagation technique on a minicomputer.

    Related Experiment Videos

    Last Updated: Jun 7, 2026

    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

  • Analyzed network component statistics to derive a classification probability calculation.
  • Acquired photon-limited images of printed characters using a photon-counting camera.

    • Main Results:

    • The neural network successfully classified photon-limited images of printed characters.
    • A method was established to calculate the probability of correct classification.
    • Experimental results demonstrated excellent agreement with theoretical predictions.
    • The backpropagation technique proved effective for training the network.

    Conclusions:

    • Neural networks are effective for classifying photon-limited images.
    • The developed method provides a reliable way to estimate classification accuracy.
    • The study validates the theoretical framework and experimental approach for photon-limited image analysis.