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 Video

Updated: Mar 31, 2026

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline
09:27

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Published on: January 30, 2019

7.5K

Closed-Loop Restoration Approach to Blurry Images Based on Machine Learning and Feedback Optimization.

Saqib Yousaf, Shiyin Qin

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |October 30, 2015
    PubMed
    Summary

    This study introduces a novel feedback control method for blind image deconvolution (BID), enhancing stability and automating parameter selection. The approach combines machine learning with feedback optimization for superior image restoration results.

    Related Concept Videos

    Focusing of Light in the Eye01:16

    Focusing of Light in the Eye

    7.4K
    Light rays enter the eye through the cornea, a transparent dome-shaped tissue that is the eye's outermost layer. The cornea bends or refracts, light rays traveling to the pupil. The shape of the cornea determines how much of the light is bent and whether the image will be focused correctly on the retina at the back of the eye. Once the light has passed through both refraction layers, it converges into a single focal point onto a small area. This is where photoreceptors start transforming...
    7.4K

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    [Application of autologous pedicled nasal mucosal flaps by "three-step" strategy in repairing of cerebrospinal fluid leakage following transsphenoidal pituitary adenoma surgery].

    Lin chuang er bi yan hou tou jing wai ke za zhi = Journal of clinical otorhinolaryngology head and neck surgery·2025
    Same author

    Real-Time Detection of Concealed Threats with Passive Millimeter Wave and Visible Images via Deep Neural Networks.

    Sensors (Basel, Switzerland)·2021
    Same author

    Deep learning based joint segmentation and characterization of multi-class retinal fluid lesions on OCT scans for clinical use in anti-VEGF therapy.

    Computers in biology and medicine·2021
    Same author

    High-Precision Detection of Defects of Tire Texture Through X-ray Imaging Based on Local Inverse Difference Moment Features.

    Sensors (Basel, Switzerland)·2018
    Same author

    Skin image segmentation based on energy transformation.

    Journal of biomedical optics·2004

    Area of Science:

    • Computer Vision
    • Image Processing
    • Control Systems

    Background:

    • Blind image deconvolution (BID) is an ill-posed problem requiring recovery of both the Point Spread Function (PSF) and the clear image from degraded input.
    • Existing BID algorithms face challenges due to diverse image degradations and often require manual parameter tuning, leading to sub-optimal results.

    Purpose of the Study:

    • To enhance the stability and automation of blind image deconvolution (BID) using a closed-loop feedback control system.
    • To develop a robust method for estimating the Point Spread Function (PSF) without manual parameter selection.

    Main Methods:

    • Employed feedback control to stabilize BID by optimizing PSF estimation quality.
    • Developed a novel quality metric based on deconvolved patch blur assessment.

    Related Experiment Videos

    Last Updated: Mar 31, 2026

    Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline
    09:27

    Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

    Published on: January 30, 2019

    7.5K
  • Utilized Kalman filter-based extremum seeking for optimal parameter control.
  • Integrated machine learning algorithms (multilayer perceptron, bagged decision trees) for PSF support size estimation.
  • Applied a multi-objective genetic algorithm for efficient key patch selection.

    • Main Results:

    • The proposed closed-loop scheme significantly outperforms open-loop methods in image deconvolution.
    • The system effectively automates restoration parameter selection, reducing reliance on manual tuning and assumptions.
    • Improved stability and accuracy in recovering both the clear image and the PSF.

    Conclusions:

    • The integration of feedback control and machine learning offers a powerful and stable approach to blind image deconvolution.
    • This method provides a more robust and automated solution for image restoration challenges.
    • The developed quality metric and optimization techniques advance the field of image deconvolution.