PSNR计算

purpose_857

im1=imread('lena2.bmp');
4 f( f% S0 [' L) V: K* C%im1=im2double(im1);
8 Z3 H5 ^. @2 H+ c) V+ ]im2=imread('lena_rbhv.bmp');
2 S' p* R1 J5 d7 V%im2=im2double(im2);
   
9 W  F4 L6 h$ M$ B' P4 ]2 ~6 cif (size(im1))~=(size(im2))
6 j# c8 T% v' ?    error('错误：两个输入图象的大小不一致');
) q  C. _, j- ]5 p% gend
" z  k3 `" X+ K# B2 J- B
    [m,n] = size(im1);
8 y0 g) k1 V+ {% z4 K    A = double(im1);
; R' p( W% R' U$ _' o    B = double(im2);
    D = sum( sum( (A-B).^2 ) );%||A-B||^2
    MSE = D / (m * n);
3 h& ~" S; f7 v( O0 ]* Zif  D == 0
    error('两幅图像完全一样');
3 w4 r; q4 o& {( }" B1 J0 @    PSNR = 200;
else
( `) _* L- t: r: U3 R$ x    PSNR = 10*log10( (255^2) / MSE );                                                        
8 S  S  P! N* T2 [3 i( P7 D8 K4 Tend
/ o: e% b7 q3 ~$ h
: t  V# `6 h+ s2 F& y/ c# m2 V
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.
$ y% s; {8 [6 c2 m6 O$ [
! L% ^. M2 ~( P( u5 L5 E! [9 ~Error in ==> PSNR_ERRO at 14
    D = sum( sum( (A-B).^2 ) );%||A-B||^2
, A. x, B& X* M

I_believe

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

peerless2021

function main()
clc; close all;
/ ?9 h5 D: B6 b8 R; j; PI=imread('cameraman.tif'); %用的是原图
8 \9 }+ |% g3 j! Q& l# TI1=imnoise(I,'gaussian',0,0.01);
( X; z" x5 E/ D# n7 M/ Vfigure;
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)
% ]' g) p- z% Q% 图像峰值信噪比PSNR、均方根误差MSE
function [PSNR, MSE] = psnr(X, Y)
% 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
: C. g4 I$ q, T2 R* ?
, e" R& [6 ~0 Z7 L. W+ B' r- Aif nargin<2
    D = X;
; x3 K% e. _; S+ S0 welse
    if any(size(X)~=size(Y))
        error('The input size is not equal to each other!');
- A% a2 ~2 S6 p& H. g9 k) m0 g    end
    D = X-Y;
: @8 |& I' f7 m  w# nend
) h  A% @) j5 F& z1 u3 IMSE = sum(D(: ).*D(: ))/prod(size(X));
PSNR = 10*log10(255^2/MSE);
4 S; S1 P1 i4 wfunction main()
clc; close all;
I=imread('cameraman.tif'); %用的是原图
I1=imnoise(I,'gaussian',0,0.01);
figure;
7 ~; L! Q" n5 V) ]7 V2 _# xsubplot(1, 2, 1); imshow(I); title('原图像');
subplot(1, 2, 2); imshow(I1); title('加噪声图像');
& d+ \9 `/ M! F0 V7 t[PSNR, MSE] = psnr(I, I1)
* z" k& Y2 L. J% x+ A% 图像峰值信噪比PSNR、均方根误差MSE
+ M, e0 E+ l; u" z9 ~& Qfunction [PSNR, MSE] = psnr(X, Y)
# P5 A! ^. Q$ k% 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
" ]! ^4 K# Q% q: a* D% w
9 @  `# p7 ~+ q2 c. J: tif nargin<2
    D = X;
* H3 \* ^9 v/ L! kelse
    if any(size(X)~=size(Y))
        error('The input size is not equal to each other!');
    end
    D = X-Y;
end
( v" d- K; D/ p/ q" D" x5 C; q) bMSE = sum(D(: ).*D(: ))/prod(size(X));
+ N8 Y* T0 B0 ]$ oPSNR = 10*log10(255^2/MSE);
用这个算法算下吧，I为原图 I1为加噪图像