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

Blind image quality assessment using a general regression neural network.

Chaofeng Li, Alan Conrad Bovik, Xiaojun Wu

    IEEE Transactions on Neural Networks
    |April 14, 2011
    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 sunflower-morphology-inspired miniature multi-DOF resonant piezoelectric actuator using combined elastic structure design.

    Ultrasonics·2026
    Same author

    Rapid detection of raw meat freshness using deep learning and colorimetric/fluorescent array.

    Food chemistry·2026
    Same author

    Integrated transcriptomic and metabolomic profiles analysis reveals a potential gene-metabolite network associated with anthocyanin-mediated color variation in maize kernels.

    Frontiers in plant science·2026
    Same author

    Bio-inspired miniature self-moving ultrasonic piezoelectric actuator: combinatorial design, analysis, and experimental investigation.

    Ultrasonics·2026
    Same author

    CCR4-associated factor CAF1I promotes plant growth and ectomycorrhizal formation in Populus tomentosa.

    Mycorrhiza·2026
    Same author

    Serial PNA-Transformer-Based Virtual Screening Identifies Nanomolar DYRK1A Inhibitors for Pancreatic Ductal Adenocarcinoma.

    ACS medicinal chemistry letters·2026
    Same journal

    Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

    IEEE transactions on neural networks·2013
    Same journal

    Guest editorial: special section on white box nonlinear prediction models.

    IEEE transactions on neural networks·2011
    Same journal

    Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

    IEEE transactions on neural networks·2011
    Same journal

    Guest editorial: special section on data-based control, modeling, and optimization.

    IEEE transactions on neural networks·2011
    Same journal

    Neural network-based multiple robot simultaneous localization and mapping.

    IEEE transactions on neural networks·2011
    Same journal

    Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

    IEEE transactions on neural networks·2011
    See all related articles

    This study introduces a novel no-reference image quality assessment algorithm using a general regression neural network (GRNN). The algorithm accurately predicts image quality based on features like phase congruency and entropy, aligning well with human judgment.

    Area of Science:

    • Computer Vision
    • Image Processing
    • Machine Learning

    Background:

    • Objective image quality assessment is crucial for various applications.
    • Existing methods often require reference images or struggle with diverse distortions.
    • Human subjective assessment is the gold standard but is time-consuming and costly.

    Purpose of the Study:

    • To develop a no-reference image quality assessment (QA) algorithm.
    • To achieve QA that aligns closely with human subjective judgment.
    • To utilize a general regression neural network (GRNN) for image quality estimation.

    Main Methods:

    • A no-reference QA algorithm was developed using a general regression neural network (GRNN).
    • Key features extracted from distorted images include mean and entropy of phase congruency, image entropy, and image gradient.

    Related Experiment Videos

  • The GRNN was trained to approximate the relationship between these features and subjective mean opinion scores.

    • Main Results:

    • The developed algorithm successfully assesses image quality across various distortion types.
    • The algorithm's predictions showed close agreement with human subjective judgments.
    • The selected features proved effective for no-reference image quality estimation.

    Conclusions:

    • The proposed GRNN-based no-reference QA algorithm is effective and reliable.
    • The method offers a viable alternative to subjective assessments for image quality evaluation.
    • This approach demonstrates the potential of machine learning in objective image quality analysis.