5.0

5.0 | 3 ratings Rate this file 98 Downloads (last 30 days) File Size: 123 KB File ID: #29500
image thumbnail

Image Error Measurements

by

 

Measures the differences between 2 images, and measurement of image quality.

| Watch this File

File Information
Description

main executing reference usage: usage_errorMeasurementsOfImages.m
-----------------------------------------------------------------------------
The objective is to measure the differences between 2 images, and measurement of image quality.
1. Mean squared error, MSE
2. Root Mean squared error, RMSE
3. Peak signal to signal noise ratio, PSNR
4. Mean absolute error, MAE
5. Signal to signal noise ratio, SNR
6. Universal Image Quality Index
7. Enhancement Measurement Error, EME
8. Pearson Correlation Coefficient

Sample output:
--------------
PSNR = +13.81915 dB
MSE = 108.53790
RMSE = 10.41815
Universal Image Quality Index = 0.16077
EME (original image) = 14.50599
EME (noisy image) = 8.48040
PearsonCorrelationCoefficient (originalImage vs noisyImage) = 30959.27033
PearsonCorrelationCoefficient (originalImage vs originalImage) = 50624.00000
SNR = -10.28091 dB
MAE = 19.82882

Caveat: For reference purposes.

The author also recommends:
http://www.mathworks.co.uk/matlabcentral/fileexchange/25005-image-picture-quality-measures

The author appreciates suggestions and errata. Please do not hesitate to send suggestions and feedback for improvement for the framework construction to the email provided.

Email: promethevx@yahoo.com.

Thank you.

Regards,
Michael Chan JT

MATLAB release MATLAB 7.10 (R2010a)
Tags for This File   Please login to tag files.
Please login to add a comment or rating.
Comments and Ratings (5)
05 Mar 2014 Tirupal Talari  
23 Feb 2012 Michael Chan

Hi Shashi,
The utilities works with image of MxN (where M != N) as well.

Try insert these lines as a test starting from line 23 in usage sample code (usage_errorMeasurementsOfImages.m) :

M = 225; N = 150;
IMG = imresize(IMG, [M N], 'bicubic');

I hope this is clear. You may wish to email me for further inquires, as it is easier to trace the comments in my inbox. I hope it helps.
Thank you.

23 Feb 2012 Shashi

Can you please send the code for its implementation in case the size of image is M by N.

28 Apr 2011 Peter ?  
29 Jan 2011 Sean

Very comprehensive.

Contact us