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 Videos

Superresolution of binary images with a nonlinear interpolative neural network.

C A Dávila, B R Hunt

    Applied Optics
    |March 18, 2008
    PubMed
    Summary

    This study explores neural networks for superresolution, enhancing image bandwidth beyond optical limits. The feedforward multilayer perceptron network acts as a nonlinear spatial interpolator for real-time superresolution applications.

    Related Concept Videos

    Super-resolution Fluorescence Microscopy01:37

    Super-resolution Fluorescence Microscopy

    Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been developed.
    Reconstruction of Signal using Interpolation01:10

    Reconstruction of Signal using Interpolation

    Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next sampling...

    You might also read

    Related Articles

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

    Sort by
    Same author

    Backpropagation algorithms and Reservoir Computing in Recurrent Neural Networks for the forecasting of complex spatiotemporal dynamics.

    Neural networks : the official journal of the International Neural Network Society·2020
    Same author

    Signal-detection tradeoff-analysis of optical vs digital Fourier transform computers.

    Applied optics·2010
    Same author

    Optical computing for image bandwidth compression: analysis and simulation.

    Applied optics·2010
    Same author

    Comparison of image restoration methods.

    Applied optics·2010
    Same author

    Training of a neural network for image superresolution based on a nonlinear interpolative vector quantizer.

    Applied optics·2008
    Same author

    A vector quantizer for image restoration.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008

    Area of Science:

    • Optics and Photonics
    • Image Processing
    • Artificial Intelligence

    Background:

    • Superresolution extends the bandwidth of diffraction-limited spectra beyond the optical passband.
    • Existing iterative superresolution algorithms are often unsuitable for real-time applications.
    • Neural network approaches to superresolution remain largely unexplored.

    Purpose of the Study:

    • To investigate the efficacy of a feedforward neural network, specifically a multilayer perceptron, for superresolution.
    • To demonstrate the network's capability in extending spectral bandwidth beyond the optical passband.
    • To evaluate the network's performance on simulated blurred images.

    Main Methods:

    • Utilized a feedforward multilayer perceptron neural network architecture.
    • Simulated binary images degraded by a diffraction-limited, circular-aperture optical transfer function.
    • Sampled images at the Nyquist rate to prevent aliasing.
    • Trained the network to perform nonlinear spatial interpolation and frequency domain extrapolation.

    Main Results:

    • The neural network successfully performed superresolution on simulated images.
    • The network acted as a nonlinear spatial interpolator, avoiding aliasing.
    • Simultaneous extrapolation in the frequency domain was achieved.
    • Demonstrated potential for real-time superresolution processing.

    Conclusions:

    • Feedforward neural networks, particularly multilayer perceptrons, offer a viable alternative to iterative methods for superresolution.
    • This approach enables simultaneous spatial interpolation and frequency domain extrapolation for enhanced image bandwidth.
    • The neural network method shows promise for real-time superresolution applications.

    Related Experiment Videos