基于matlab CCF算法的图像质量评价

haidaowang

源代码
8 P2 l+ A1 |8 S5 r" t' s
1 s" D$ h4 f4 n7 s0 Y``
& C* x: ]3 t, P4 C; lclear all
clc
7 p% R" R' m0 X+ v' t7 `6 t
( v$ S, M+ r3 V/ A% Pim = imread(‘1.bmp’);

quality = CCF(im)
function [quality] = CCF(im)
3 ?: O' U1 r- y. W
; b! e6 G, n1 F$ _* a%-------------CCF_coloRFulness -----------------
imColor = double(im);

3 @" ?9 q7 `! K( l- @7 K

3 H6 W- m0 V: t8 a; {$ I

• R = imColor(:,:,1);
• G = imColor(:,:,2);
• B = imColor(:,:,3);
• RR = log(R+0.00001) - mean2(log(R+0.00001));
• GG = log(G+0.00001) - mean2(log(G+0.00001));
• BB = log(B+0.00001) - mean2(log(B+0.00001));
• alpha = RR-GG;
• beta = 0.5*(RR+GG)-BB;
• mu_alpha=mean(mean(alpha));
• mu_beta=mean(mean(beta));
• var_alpha=var(var(alpha));
• var_beta=var(var(beta));
• CCF_colorfulness=1000*((sqrt(var_alpha+var_beta)+0.3*sqrt(mu_alpha*mu_alpha+mu_beta*mu_beta))/85.59);
  

' Y( A: p1 g8 S  K3 E$ z2 M( m
& h' b9 R+ Y6 Q& s%-------------CCF_contrast----------------------
8 _% m! @% \6 {0 s5 t% H
% _: y0 T2 f3 F" r2 z# f& K

• im1=rgb2gray(im);
• CCF_contrast = CCFcontrast(im1);
  

5 X" M$ ~0 a. V3 R9 \8 Y; C9 g. Y
%-------------CCF_FADE--------------------------
1 }) A/ M7 z  @0 k
& O, H; y  g4 Y1 d4 c" _

• CCF_FADE = FADE(im);
  + v# W% {) ^  j/ z' H

4 m, q$ t1 W% @# C. o- m8 Y
%------------ normalization ------------------
. `; t. e5 ]5 t% A! o$ T6 [  n1 v
/ @4 d$ p. {4 X$ O- O# @! J+ c

• CCF_colorfulness=mapminmax(CCF_colorfulness,1,10);
• CCF_contrast=mapminmax(CCF_contrast,1,10);
• CCF_FADE=10-mapminmax(CCF_FADE,1,10);
  

+ w; J# X* N: |
% ------------calculate image quality with coefficients---------------------
2 ~2 v9 \1 p, e* o3 Q, q" s. r0 i  Y

• c=[0.17593 0.61759 0.33988 ];
• quality = c(1)*(CCF_colorfulness) + c(2)*(CCF_contrast) + c(3)*(CCF_FADE)
  # C1 q& l( Q1 C

# L( R( x" ?( Z& l
end

& v, l* m* t! S: C% t) _7 Q
8 R2 Y. [; b6 \, o3 `

NNNei256

基于matlab CCF算法的图像质量评价

twel2e

可以借鉴一下
; t3 Y, H2 o6 ^( t% L8 E7 \
% H; p3 {7 T5 g* [# {3 `