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

Specification of the observation model for regularized image up-sampling.

Hussein A Aly1, Eric Dubois

  • 1Ministry of Defence, Cairo, Egypt. haly@ieee.org

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|May 13, 2005
PubMed
Summary

This study introduces a new algorithm to determine the observation model for image up-sampling. Adapting this model improves regularization-based super-resolution results by accurately reflecting image acquisition processes.

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

Co-inoculation with deformed wing virus and sacbrood virus affects viral and immune dynamics and synergistically increases honey bee mortality.

PLoS pathogens·2026
Same author

Impact of Delayed Heparin Bridging on Bleeding and Stroke After Left Ventricular Assist Device Implantation.

ASAIO journal (American Society for Artificial Internal Organs : 1992)·2026
Same author

Complications of microaxial flow pump and VA-ECMO in infarct-related cardiogenic shock: Insights from the Netherlands heart registration.

International journal of cardiology·2025
Same author

Genotype B of deformed wing virus and related recombinant viruses become dominant in European honey bee colonies.

Scientific reports·2025
Same author

Alteration of mechanical stresses in the murine brain by age and hemorrhagic stroke.

PNAS nexus·2024
Same author

Distribution of infectious and parasitic agents among three sentinel bee species across European agricultural landscapes.

Scientific reports·2024

Area of Science:

  • Image processing
  • Computer vision
  • Signal processing

Background:

  • Image up-sampling is an ill-posed inverse problem.
  • Regularization methods are promising for super-resolution.
  • A crucial component is the observation model within the data-fidelity term.

Purpose of the Study:

  • To present an algorithm for determining the observation model for image up-sampling.
  • To model the physical acquisition processes of low-resolution (LR) and high-resolution (HR) images.
  • To improve the accuracy of regularization-based super-resolution.

Main Methods:

  • Developing an algorithm to derive the observation model.
  • Modeling LR and HR camera acquisition processes (e.g., Gaussian or rectangular apertures).

Related Experiment Videos

  • Integrating the derived model into the data-fidelity term of regularization cost functions.

    • Main Results:

    • Demonstrated the importance of using a correct, adapted observation model.
    • Showcased improved performance in regularized image up-samplers.
    • Validated the method with scenarios involving different camera aperture models.

    Conclusions:

    • The proposed algorithm effectively determines the observation model for image up-sampling.
    • Using an adapted observation model significantly enhances super-resolution performance.
    • This approach is crucial for accurate regularization-based image restoration.