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

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

C A Dávila1, B R Hunt

  • 1Department of Electrical and Computer Engineering, University of Arizona, Tucson, Arizona 85721, USA. cadavila@ece.arizona.edu

Applied Optics
|March 20, 2008
PubMed
Summary

This study introduces a neural network approach for superresolution, enhancing image quality by extending the spectrum beyond optical limits. Vector quantization aids in creating training data for improved neural network performance in image restoration.

Related Concept Videos

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...
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.

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

Superresolution of binary images with a nonlinear interpolative neural network.

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:

  • Diffraction-limited imaging restricts resolution.
  • Superresolution techniques aim to overcome these limitations.
  • Neural networks offer a promising approach for image restoration.

Purpose of the Study:

  • To apply a neural network approach for image superresolution.
  • To address image degradation from diffraction blur and additive noise.
  • To introduce a novel method for generating training data using vector quantization.

Main Methods:

  • Simulated gray-scale images were used.
  • Images were degraded by diffraction blur and additive noise.
  • A nonlinear vector quantizer trained for codebook generation was used for supervised neural network training via backpropagation.

Related Experiment Videos

Main Results:

  • The neural network approach demonstrated effectiveness in superresolution.
  • The method successfully extended the spectrum of diffraction-limited images.
  • Vector quantization provided a novel way to generate training datasets.

Conclusions:

  • Neural networks, combined with vector quantization, offer a viable method for image superresolution.
  • The approach can restore images degraded by blur and noise.
  • This technique advances the field of computational imaging.