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

Background estimation in nonlinear image restoration.

G M van Kempen1, L J van Vliet

  • 1Central Analytical Sciences, Unilever Research Vlaardingen, The Netherlands.

Journal of the Optical Society of America. A, Optics, Image Science, and Vision
|March 9, 2000
PubMed
Summary

Nonlinear image restoration algorithms rely on accurate background estimation for effective nonnegativity constraints. Improper background estimation, whether under or over, significantly impacts restoration performance, necessitating improved methods for scientific imaging.

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

Orientation Prior and Consistent Model Selection Increase Sensitivity of Tract-Based Spatial Statistics in Crossing-Fiber Regions.

IEEE transactions on medical imaging·2019
Same author

Comparison between dynamic gadoxetate-enhanced MRI and <sup>99m</sup>Tc-mebrofenin hepatobiliary scintigraphy with SPECT for quantitative assessment of liver function.

European radiology·2019
Same author

A toolkit for the characterization of CCD cameras for transmission electron microscopy.

Acta crystallographica. Section D, Biological crystallography·2010
Same author

DNA deformations near charged surfaces: electron and atomic force microscopy views.

Biophysical journal·2009
Same author

Quantitative image analysis for evaluating the coating thickness and pore distribution in coated small particles.

Pharmaceutical research·2008
Same author

Protrusion method for automated estimation of polyp size on CT colonography.

AJR. American journal of roentgenology·2008

Area of Science:

  • Image restoration
  • Computational imaging
  • Scientific data analysis

Background:

  • Nonlinear image restoration algorithms offer nonnegativity constraints, unlike linear filters.
  • The effectiveness of nonnegativity constraints in algorithms like iterative constrained Tikhonov-Miller (ICTM) depends on accurate background estimation.
  • Existing methods may not adequately address the sensitivity of these algorithms to background levels.

Purpose of the Study:

  • To quantitatively assess the impact of background estimation on nonlinear image restoration algorithms.
  • To compare the performance of ICTM, Carrington, and Richardson-Lucy algorithms against linear Tikhonov-Miller filters concerning background estimation.
  • To develop and validate a novel background estimation method for nonlinear restoration.

Main Methods:

Related Experiment Videos

  • Quantitative analysis of ICTM, Carrington, and Richardson-Lucy algorithms' performance under varying background estimations.
  • Comparison with the linear Tikhonov-Miller restoration filter.
  • Development and application of a new general background estimation method.

Main Results:

  • Algorithm performance is critically dependent on background estimation accuracy.
  • Underestimating background renders the nonnegativity constraint ineffective, similar to linear filter performance.
  • Slight overestimation of background severely degrades performance by clipping object intensities.

Conclusions:

  • Accurate background estimation is crucial for the successful application of nonnegativity constraints in nonlinear image restoration.
  • A novel, general background estimation method has been developed and demonstrated on real confocal images.
  • The proposed method addresses the critical dependency of nonlinear restoration algorithms on background levels.