Demo
Images and Free Software for "A Universal Image Quality Index"
See the SSIM Index Page for an improved version
of the algorithm!!!
Demo 1: "Lena" image with different types
of distortions
Demo 2: "Goldhill" image with different
types of distortions
Demo 3: "Couple" image with different types
of distortions
Demo 4: "Tiffany", "Lake" and
"Mandrill" images with JPEG compression
Demo 5: "Woman", "Man" and
"Barbara" images with blurring
An efficient Matlab implementation of the proposed
universal image quality index algorithm is available here. You can download it
for free, change it as you like and use it anywhere, but please refer to its
original source (cite our paper and this web page).
This program takes
about 2.4 seconds to calculate the quality of a 512 by 512 gray scale image on
my 1G Hz Pentium III computer. My more efficient C implementation is more than
15 times faster than this Matlab program.
More insights
related to this method is described in another paper: Why is image quality assessment so
difficult?
Back to Full-Reference Quality Assessment Research Work
Back to LIVE