PSNR计算

purpose_857

im1=imread('lena2.bmp');
%im1=im2double(im1);
im2=imread('lena_rbhv.bmp');
  H5 ^( F: F1 w5 H: L2 M0 W! i- N+ d%im2=im2double(im2);
1 v/ ^; g8 x# q   
if (size(im1))~=(size(im2))
    error('错误：两个输入图象的大小不一致');
end

' P- L3 E' A* H, _( F3 X7 N( B$ G+ s    [m,n] = size(im1);
- K) z% D( A9 b3 H/ }1 ?    A = double(im1);
4 Q1 |# ~: i; }6 n    B = double(im2);
    D = sum( sum( (A-B).^2 ) );%||A-B||^2
    MSE = D / (m * n);
if  D == 0
: P: j" ]/ f( s3 k  k  o    error('两幅图像完全一样');
6 k6 T, s3 T/ R$ P! q' h    PSNR = 200;
9 a& P! p( ^: w6 @else
- n$ M  a" Y- h6 Z! }    PSNR = 10*log10( (255^2) / MSE );                                                        
7 U+ _0 F& p. \9 a9 zend


' n6 x! y$ c& w/ w$ b! S: N从网上COPY了下 稍微改了下  我不知道这一行为什么出错  请指教
??? Subscript indices must either be real positive integers or logicals.
  q+ V8 W) w, L4 ?  c; N
Error in ==> PSNR_ERRO at 14
5 F. B- `' m, |7 ^1 v! y5 V6 ]8 @    D = sum( sum( (A-B).^2 ) );%||A-B||^2
& }+ ?: q+ |& Z5 F) r

I_believe

D = sum( sum( (A-B).^2 ) );指的是什么，为什么有两从sum？

peerless2021

function main()
* l: {, y/ Q, I; Sclc; close all;
I=imread('cameraman.tif'); %用的是原图
I1=imnoise(I,'gaussian',0,0.01);
figure;
subplot(1, 2, 1); imshow(I); title('原图像');
1 }$ e, V$ f5 E1 zsubplot(1, 2, 2); imshow(I1); title('加噪声图像');
[PSNR, MSE] = psnr(I, I1)
! U) _  ~; ^4 @  I/ ~& t% 图像峰值信噪比PSNR、均方根误差MSE
1 j/ H* a0 R; x, rfunction [PSNR, MSE] = psnr(X, Y)
% 计算峰值信噪比PSNR、均方根误差MSE
& w/ B0 c( b6 _, L8 \% 如果输入Y为空，则视为X与其本身来计算PSNR、MSE

; g# z: R, M8 Tif nargin<2
    D = X;
else
5 p& y! M1 D, ]' ?* L1 }    if any(size(X)~=size(Y))
% f2 x( d; y7 {) ?        error('The input size is not equal to each other!');
    end
% T2 q# g" N" C    D = X-Y;
end
1 q, U5 Q9 C; u8 @$ T5 s1 k5 V7 ZMSE = sum(D(: ).*D(: ))/prod(size(X));
3 r8 N; W% C. zPSNR = 10*log10(255^2/MSE);
function main()
# Y# p. A1 k  R; G+ wclc; close all;
I=imread('cameraman.tif'); %用的是原图
I1=imnoise(I,'gaussian',0,0.01);
figure;
subplot(1, 2, 1); imshow(I); title('原图像');
subplot(1, 2, 2); imshow(I1); title('加噪声图像');
[PSNR, MSE] = psnr(I, I1)
  G4 |8 v7 a3 T) P% n1 h/ v% 图像峰值信噪比PSNR、均方根误差MSE
+ J/ n, K& u# y$ _- Z0 jfunction [PSNR, MSE] = psnr(X, Y)
; ?; _8 p+ f9 A! Z6 K' W% 计算峰值信噪比PSNR、均方根误差MSE
% 如果输入Y为空，则视为X与其本身来计算PSNR、MSE
% S# _/ K5 W: Z: C9 p/ k, _& y: }
if nargin<2
    D = X;
else
    if any(size(X)~=size(Y))
        error('The input size is not equal to each other!');
8 z/ N- m- P, y$ J2 n    end
4 t3 d8 H' I6 `+ u' m* [. ?    D = X-Y;
end
; Z3 [% h6 t+ O; p+ lMSE = sum(D(: ).*D(: ))/prod(size(X));
PSNR = 10*log10(255^2/MSE);
用这个算法算下吧，I为原图 I1为加噪图像