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

A convolutional neural network approach for objective video quality assessment.

Patrick Le Callet1, Christian Viard-Gaudin, Dominique Barba

  • 1Institut de Recherche en Communication et Cybernétique de Nantes, University of Nantes, Nantes 44306, France. patrick.lecallet@univ-nantes.fr

IEEE Transactions on Neural Networks
|September 28, 2006
PubMed
Summary

This study introduces a novel neural network approach for objective video quality assessment, aiming to automatically predict human perception. The method achieves high correlation with subjective scores, offering an efficient alternative to traditional methods.

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

Multi-Dimensional Quality Assessment for Single-Image-to-3D Contents: Dataset and Model.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Subjective and Objective Audio-Visual Quality Assessment for Omnidirectional Videos.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025
Same author

ESIQA: Perceptual Quality Assessment of Vision-Pro-based Egocentric Spatial Images.

IEEE transactions on visualization and computer graphics·2025
Same author

Interactions Between Vibroacoustic Discomfort and Visual Stimuli: Comparison of Real, 3D and 360 Environments.

IEEE transactions on visualization and computer graphics·2025
Same author

Confusing Image Quality Assessment: Toward Better Augmented Reality Experience.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2022
Same author

UIF: An Objective Quality Assessment for Underwater Image Enhancement.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2022

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Signal Processing

Background:

  • Subjective video quality assessment is complex and time-consuming.
  • Objective metrics aim to emulate human judgment for digital video quality.
  • Reduced-reference (RR) metrics offer a balance between accuracy and efficiency.

Purpose of the Study:

  • To develop an objective video quality measurement method using neural networks.
  • To create a reduced-reference (RR) quality metric that emulates human perception.
  • To improve the prediction of subjective quality scores obtained via the single stimulus continuous quality evaluation (SSCQE) method.

Main Methods:

  • Application of a convolutional neural network (CNN) for continuous time scoring.
  • Extraction of objective features frame-by-frame from reference and distorted videos.

Related Experiment Videos

  • Integration of features along the temporal axis using a time-delay neural network (TDNN).

    • Main Results:

    • The proposed CNN-TDNN approach effectively models temporal pooling from the human vision system (HVS).
    • Achieved a linear correlation coefficient of up to 0.92 between objective and subjective scores for MPEG-2 videos.
    • Demonstrated effectiveness on videos with bit rates ranging from 2-6 Mb/s.

    Conclusions:

    • Neural networks, particularly CNNs and TDNNs, offer a powerful tool for objective video quality assessment.
    • The developed RR metric accurately predicts subjective video quality, aligning with VQEG standards.
    • This approach provides a more efficient and reliable method for evaluating perceived video quality.