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

Relaxed ordered-subset algorithm for penalized-likelihood image restoration.

Saowapak Sotthivirat1, Jeffrey A Fessler

  • 1Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, Michigan 48109, USA. ssotthiv@umich.edu

Journal of the Optical Society of America. A, Optics, Image Science, and Vision
|March 13, 2003
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

A vendor-neutral functional MRI acquisition protocol for multi-site studies.

Aperture neuro·2026
Same author

Phantom- and simulation-based validation of combined diffusion relaxometry in ex vivo ADRD white matter.

bioRxiv : the preprint server for biology·2026
Same author

Smooth optimization using global and local low-rank regularizers.

SIAM journal on imaging sciences·2026
Same author

Bilevel Optimized Implicit Neural Representation for Scan-Specific Accelerated MRI Reconstruction.

IEEE transactions on medical imaging·2026
Same author

Scan-Adaptive MRI Undersampling Using Neighbor-based Optimization (SUNO).

IEEE transactions on computational imaging·2026
Same author

Spatiotemporal Maps for Dynamic MRI Reconstruction.

IEEE transactions on computational imaging·2026

The new relaxed ordered-subset, separable-paraboloidal-surrogate (OS-SPS) algorithm accelerates image restoration. This method ensures convergence, offering a significant speedup over traditional expectation-maximization (EM) algorithms for efficient image recovery.

Area of Science:

  • Image processing and computational imaging.
  • Optimization algorithms in scientific computing.

Background:

  • Expectation-maximization (EM) algorithm offers guaranteed convergence for image recovery but is slow.
  • Ordered-subset EM (OS-EM) accelerates convergence but lacks guaranteed convergence.
  • Relaxed OS-SPS algorithm shows promise for convergence and speed in tomography.

Purpose of the Study:

  • Adapt the relaxed OS-SPS algorithm for image restoration.
  • Address challenges in data acquisition strategies for image restoration compared to tomography.
  • Develop a faster and reliably converging algorithm for image restoration.

Main Methods:

  • Adapted the relaxed OS-SPS algorithm for image restoration tasks.
  • Implemented a novel subset selection strategy using pixel locations.

Related Experiment Videos

  • Conducted simulations to evaluate algorithm performance.

    • Main Results:

    • The adapted relaxed OS-SPS algorithm achieves order-of-magnitude acceleration over the EM algorithm.
    • The new algorithm provides guaranteed convergence for image restoration.
    • Simulation results demonstrate significant efficiency gains.

    Conclusions:

    • The relaxed OS-SPS algorithm is effective for accelerating image restoration.
    • This method combines speed and guaranteed convergence, crucial for efficient image recovery.
    • The pixel-based subset strategy is suitable for image restoration applications.