Skip to content

A laboratory for experimenting with objective image/video quality assessment metrics.

License

Notifications You must be signed in to change notification settings

cheraaqee/IQA_Lab

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

IQA_Lab

The goal of objective quality assessment (QA) methods is to generate a score for the input visual signal. This score must correlate with human perception of quality.

(i.e. , if we beleive the quality of the image/video under test is fine, the algorithm must generate a higher score for that image/video. )

(The definitons are not precise! more can be found here: https://ocampor.medium.com/advanced-methods-for-iqa-37581ec3c31f ;-) https://en.wikipedia.org/wiki/Structural_similarity )

There are datasets of images/videos along with their human-rated scores. The objective algorithm generates a score for each sample. Then, the correlation between the objective and subjective scores is desired to be high.

This repository doesn't tend to merely automate the testing procedures for different datasets and its ultimate goal is to analyse and visualize the data to gain different insights on methods' performance.

About

A laboratory for experimenting with objective image/video quality assessment metrics.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published