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

Adaptive calibration of imaging array detectors.

M Budinich1, R Frison

  • 1Dipartimento di Fisica, Universita degli Studi de Trieste, Via Valerio 2, I-34127 Trieste, Italy. mbh@trieste.infn.it

Neural Computation
|July 29, 1999
PubMed
Summary

We developed two neural network methods for correcting nonuniformity in imaging array detectors without calibration. These techniques enhance image quality by adapting to detector properties and maximizing output entropy for better data.

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

RadioLab project: knowledge of radon gas in Italy.

Scientific reports·2024
Same author

Electromagnetic levitation containerless processing of metallic materials in microgravity: thermophysical properties.

NPJ microgravity·2023
Same author

Crystallization of zirconia based thin films.

Physical chemistry chemical physics : PCCP·2015
Same author

A self-organizing neural network for the traveling salesman problem that is competitive with simulated annealing.

Neural computation·1996
Same author

Sorting with self-organizing maps.

Neural computation·1995

Area of Science:

  • * Applied Physics
  • * Machine Learning
  • * Image Processing

Background:

  • * Nonuniformity in imaging array detectors degrades image quality and requires calibration.
  • * Existing calibration methods are often time-consuming and may not adapt to changing detector conditions.

Purpose of the Study:

  • * To introduce two novel, calibration-free methods for correcting nonuniformity in imaging array detectors using neural networks.
  • * To enhance image quality by exploiting inherent image properties and maximizing output entropy.

Main Methods:

  • * Method 1: A self-organizing neural network that applies continuous, adaptive linear correction to raw detector data.
  • * Method 2: Utilizing a contrast equalization curve to adjust pixel distributions for improved uniformity.

Related Experiment Videos

Main Results:

  • * Both methods successfully correct detector nonuniformity without explicit calibration.
  • * The techniques maximize the entropy of the output, leading to enhanced image quality.
  • * The proposed methods demonstrate adaptability to various imaging array detector types.

Conclusions:

  • * Neural network-based approaches offer effective calibration-free solutions for imaging array detector nonuniformity.
  • * The presented methods are versatile and applicable to diverse detector technologies, including silicon, infrared, and high-energy physics detectors.