Skip to content

Estimates the Spatio-Temporal Just Noticeable Difference (JND) profile of video frames.

License

Notifications You must be signed in to change notification settings

pneycho/temporal-CSF-model

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

18 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

temporal-CSF-model

By Shreyan Sanyal

Estimates the spatio-temporal Just Noticeable Difference profile of video frames!

This is a personal implementation of the paper "Spatio-Temporal Just Noticeable Distortion Profile for Grey Scale Image/Video in DCT Domain". If you use this code, you must cite the following paper:

Spatio-Temporal Just Noticeable Distortion Profile for Grey Scale Image/Video in DCT Domain", Zhenyu Wei and King N. Ngan, IEEE Transactions on Circuits and Systems for Video Technology, Vol.19, No.3, March 2009

Requirements:

This program requires a block-matching motion estimation algorithm to calculate the temporal JND profile. I have used the Adaptive Rood Pattern Search algorithm (The motionEstARPS function in line 136). You can download it from here. Other techniques would work as well.

MATLAB

Quickstart:

Edit (Put in the video file location) and run demo.m to get started. So,

Input:

Video file

Output:

T_JND_s = Spatial JND Profile

T_JND = Temporal JND Profile

About

Estimates the Spatio-Temporal Just Noticeable Difference (JND) profile of video frames.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages