基于matlab CCF算法的图像质量评价

haidaowang

源代码

``
clear all
clc
2 d/ {9 q2 d8 Y5 y
im = imread(‘1.bmp’);

quality = CCF(im)
/ N) q$ ]5 d' E/ Zfunction [quality] = CCF(im)
3 Y# T8 Z0 n( X# C2 P
%-------------CCF_coloRFulness -----------------
4 I6 \5 z5 F- l  OimColor = double(im);
8 i9 S2 _5 c/ |  U4 s
3 c* [: k. w  t' c: R2 Y- P
. X& T3 U' ~2 ]7 F% T
: M9 ~9 o) ^9 G  b9 q  Q- i) o! D

• 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);
  

%-------------CCF_contrast----------------------
+ |/ [9 D% b2 l% t
+ a9 V, V5 U0 \: k" d, a

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

; L' j" J7 A; r# x+ f
- N$ R) Q& T8 _! H%-------------CCF_FADE--------------------------

' b+ M- w& ^/ ?  o5 @/ \. A  i) O

• CCF_FADE = FADE(im);
  % b- I+ R; Y8 d

/ Z1 o. a) f' A& g8 y% u1 a4 r
3 M" ~! c8 n6 Q%------------ normalization ------------------
0 ?& i! @" z/ m  z& V$ |7 G4 |; d

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

9 z/ @8 U4 {! M9 i' G# m. H9 a
# N( M0 J. O" F) c& `! r% ------------calculate image quality with coefficients---------------------
& Z/ v; V7 s. r% S
- p% D9 b! i$ B3 l% [5 V/ c

• c=[0.17593 0.61759 0.33988 ];
• quality = c(1)*(CCF_colorfulness) + c(2)*(CCF_contrast) + c(3)*(CCF_FADE)
  

end


, A# C  M) [5 U4 Z$ d! p

NNNei256

基于matlab CCF算法的图像质量评价

twel2e

可以借鉴一下

7 Q- p" f* v  N2 |( v1 X9 S8 M