Related Experiment Video
Updated: Apr 16, 2026
10:41
Using Electroencephalography Measurements and High-quality Video Recording for Analyzing Visual Perception of Media Content
Published on: May 26, 2018
7.4K
EEG-based classification of video quality perception using steady state visual evoked potentials (SSVEPs).
Laura Acqualagna1, Sebastian Bosse, Anne K Porbadnigk
1Neurotechnology Group, Technische Universität Berlin, Berlin.
Journal of Neural Engineering
|March 14, 2015
Summary
This study introduces steady state visual evoked potentials (SSVEPs) as a fast, objective measure for video quality assessment using electroencephalography (EEG). SSVEPs accurately correlate with human perception, offering a viable alternative to traditional methods.
Area of Science:
- Neuroscience
- Computer Vision
- Signal Processing
Background:
- Objective measurement of perceived video quality using electroencephalography (EEG) is an emerging field.
- Existing methods often rely on the P3 component of event-related potentials.
- Steady state visual evoked potentials (SSVEPs) offer a direct link to sensory processing and potentially shorter experimental durations.
Purpose of the Study:
- To investigate steady state visual evoked potentials (SSVEPs) as EEG correlates for measuring video quality changes.
- To compare SSVEP-based objective measures with standard behavioral assessments (Mean Opinion Scores).
- To explore machine learning methods for classifying SSVEPs indicative of quality variations.
Main Methods:
- Six levels of image degradation were created using H.265/MPEG-HEVC video coding.
- Degraded images were presented in rapid alternation with original images to elicit SSVEPs.
- Two machine learning approaches were used to classify SSVEP-based neural signals.
Main Results:
- High classification accuracies were achieved for identifying neural signals above the perceptual quality change threshold.
- The classification accuracies showed a significant correlation with human-assigned Mean Opinion Scores.
- SSVEPs effectively serve as a neural marker for objectively processing video quality changes.
Conclusions:
- Objective video quality assessment using SSVEPs is a feasible complement to behavioral methods.
- SSVEP-based assessment offers a significantly faster alternative compared to P3 component-based methods.
- This approach provides a robust and efficient neural correlate for video quality perception.
