I have an image with gaussian noise and periodic noise. How to remove gaussian noise from image?

I have an image with gaussian noise and periodic noise. I want to design two filters both of gaussian and periodic. I designed filter for removing periodic noise using DCT. And It works. When I apply to filter to image,periodic noises disappeared. But comes to the gaussian noise, when I apply to the image with just gaussian noise, It works fine. But When I apply to gaussian+periodic noise, It gives nonsense output. Here is my code.

clc;
clear;
cd 'C:\Users\LENOVO\OneDrive\Masaüstü' 
I=imread('Coleen.jpg','jpg');
subplot(1,2,1);imshow(I); title('Orjinal görüntü');
J = imnoise(I,'gaussian');
[x, y]=meshgrid(1:1200,1:1400);
noise=15*sin(2*pi/30*x+2*pi/30*y);
noiseimg=double(J)+noise;
noisedct = dct2(noiseimg);
% Reduce peaky high-frequency components
idx = abs(noisedct) > 50;
idx(1:19,:) = false;
idx(:,1:19) = false;
noisedct(idx) = noisedct(idx)/100;
% Convert to image
I2 = idct2(noisedct);
I2 = mat2gray(I2);
% Show the result
imshow(I2)
title('Filtered Image','FontSize',14)
width1 = 3; sigma1 = (width1-1) / 6;
width2 = 7; sigma2 = (width2-1) / 6;
width3 = 13; sigma3 = (width3-1) / 6;
width4 = 19; sigma4 = (width4-1) / 6;

%// Create Gaussian kernels
h1 = fspecial('gaussian', [width1 width1], sigma1);
h2 = fspecial('gaussian', [width2 width2], sigma2);
h3 = fspecial('gaussian', [width3 width3], sigma3);
h4 = fspecial('gaussian', [width4 width4], sigma4);

%// Filter the image using each kernel
out1 = imfilter(noiseimg, h1, 'replicate');
out2 = imfilter(noiseimg, h2, 'replicate');
out3 = imfilter(noiseimg, h3, 'replicate');
out4 = imfilter(noiseimg, h4, 'replicate');

%// Display them all on a figure
figure;
subplot(2,2,1);
imshow(out1);
title('Width = 3');
subplot(2,2,2);
imshow(out2);
title('Width = 7');
subplot(2,2,3);
imshow(out3);
title('Width = 13');
subplot(2,2,4);
imshow(out4);
title('Width = 19');

Here is the output.

Answer 1

[yanqi liu]

clc;
clear all; close all;
I=imread('cameraman.tif');
subplot(1,2,1);imshow(I);
J = imnoise(I,'gaussian');
[x, y]=meshgrid(1:size(I,2),1:size(I,1));
noise=15*sin(2*pi/30*x+2*pi/30*y);
noiseimg=double(J)+noise;
noisedct = dct2(noiseimg);
% Reduce peaky high-frequency components
idx = abs(noisedct) > 50;
idx(1:19,:) = false;
idx(:,1:19) = false;
noisedct(idx) = noisedct(idx)/100;
% Convert to image
I2 = idct2(noisedct);
I2 = mat2gray(I2);
% Show the result
subplot(1,2,2);
imshow(I2)
title('Filtered Image','FontSize',14)

width1 = 3; sigma1 = (width1-1) / 6;
width2 = 7; sigma2 = (width2-1) / 6;
width3 = 13; sigma3 = (width3-1) / 6;
width4 = 19; sigma4 = (width4-1) / 6;

%// Create Gaussian kernels
h1 = fspecial('gaussian', [width1 width1], sigma1);
h2 = fspecial('gaussian', [width2 width2], sigma2);
h3 = fspecial('gaussian', [width3 width3], sigma3);
h4 = fspecial('gaussian', [width4 width4], sigma4);

%// Filter the image using each kernel
out1 = imfilter(noiseimg, h1, 'replicate');
out2 = imfilter(noiseimg, h2, 'replicate');
out3 = imfilter(noiseimg, h3, 'replicate');
out4 = imfilter(noiseimg, h4, 'replicate');

% Display them all on a figure
figure;
subplot(2,2,1);
imshow(out1,[]);
title('Width = 3');
subplot(2,2,2);
imshow(out2,[]);
title('Width = 7');
subplot(2,2,3);
imshow(out3,[]);
title('Width = 13');
subplot(2,2,4);
imshow(out4,[]);
title('Width = 19');

Answer 2

[Image Analyst]

I'd first get rid of periodic noise to "flatten" the image with Fourier filtering. Then I'd use a wiener filter. wiener2(), to get rid of the Gaussian noise.

Attach 'Coleen.jpg' if you need more help.

TUTORIAL: How to ask a question (on Answers) and get a fast answer

Answer 3

[Image Analyst]

Try BM3D - arguably the best image denoising algorithm out there.

I can't post the copyrighted software here.

Download the software at https://webpages.tuni.fi/foi/GCF-BM3D/