MATLAB: Low pass filter on Y U and V bands

low-pass filterMATLABy u v bands

I want to implement low pass filter on Y, U and V bands of image by a factor of 3 in both horizontal and vertical directions. I write a code but i want to confirm that whether the code which I write is correct or not? Please confirm. Code is written below:

rgbImage = imread('fav.png');
R = rgbImage(:, :, 1);
G = rgbImage(:, :, 2);
B = rgbImage(:, :, 3);
Y = 0.299*R + 0.587*G + 0.114*B; 
U = - 0.14713*R - 0.28886*G + 0.436*B; 
V = 0.615*R - 0.51499*G - 0.10001*B;
subplot(2,2,1);
imshow(rgbImage);
title('Original Image');
hsize = 3;
H = fspecial('average', hsize);
filteredY = imfilter(Y, H);
subplot(2,2,2);
imshow(filteredY);
title('filteredY');
filteredU = imfilter(U, H);
subplot(2,2,3);
imshow(filteredU);
title('filteredU');
filteredV = imfilter(V, H);
subplot(2,2,4);
imshow(filteredV);
title('filteredV');

Best Answer

Hello,

Your code seems to work correctly and it certainly does low-pass filtering on Y, U and V. You can also however, try using the gaussian low pass filter and compare the result for different sigma values with the results from the averaging filter.

You can have a look at the documentation here:

http://www.mathworks.com/help/images/ref/fspecial.html

Related Solutions

MATLAB: Error using .* Integers can only be combined with integers of the same class, or scalar doubles.

I think this is really what you were trying to do:

clc;    % Clear the command window.
close all;  % Close all figures (except those of imtool.)
clear;  % Erase all existing variables. Or clearvars if you want.
workspace;  % Make sure the workspace panel is showing.
format short g;
format compact;
fontSize = 15;
% Get noise-free original gray scale image.
grayImage = imread('eight.tif');
% Get the dimensions of the image.  
% numberOfColorChannels should be = 1 for a gray scale image, and 3 for an RGB color image.
[rows, columns, numberOfColorChannels] = size(grayImage);
% Create noisy image from it.
noisyImage = imnoise(im2double(grayImage), 'Gaussian', 0, 0.01);
% Define spatial filters as a 15x15 window.
gaussianSpatialFilter = fspecial('gaussian', 15, 1.0);
% Do a filter by blurring with a Gaussian kernel in the spatial domain:
spatialDomainFilteredImage = imfilter(noisyImage, gaussianSpatialFilter, 'replicate');
% Display results:

subplot(2, 4, 1); imshow(grayImage, []); title('Original Image', 'FontSize', fontSize); axis on;
subplot(2, 4, 2); imshow(noisyImage, []); title('Noisy Image', 'FontSize', fontSize); axis on;
subplot(2, 4, 3); imshow(gaussianSpatialFilter, []); title('Blur Kernel', 'FontSize', fontSize); axis on;
subplot(2, 4, 4); imshow(spatialDomainFilteredImage, []); title('Image filtered with Gaussian in the spatial domain', 'FontSize', fontSize); axis on;
% Define frequency domain filter the same size as the image.
gaussianFreqFilter = fspecial('gaussian', [rows, columns], 0.2*rows); % Keep the low frequencies.
% gaussianFreqFilter = ones(rows, columns); % Keep all frequencies.
% Fourier transform the noisy image.
freqDomainImage = fftshift(fft2(noisyImage));
% Now do filtering in the frequency domain
filteredFreqDomain = freqDomainImage .* gaussianFreqFilter;
% Now transform back to spatial domain:
spatialImage = real(ifft2(ifftshift(filteredFreqDomain)));
% Display results:
subplot(2, 4, 5); imshow(gaussianFreqFilter, []); title('Freq Domain Filter', 'FontSize', fontSize); axis on;
subplot(2, 4, 6); imshow(log(abs(freqDomainImage)), []); title('Original Freq Domain Image', 'FontSize', fontSize); axis on;
subplot(2, 4, 7); imshow(log(abs(filteredFreqDomain)), []);  title('Filtered Freq Domain Image', 'FontSize', fontSize); axis on;
subplot(2, 4, 8); imshow(spatialImage, []); title('Back in Spatial Domain', 'FontSize', fontSize); axis on;
% Set up figure properties:
% Enlarge figure to full screen.
set(gcf, 'Units', 'Normalized', 'OuterPosition', [0, 0.04, 1, 0.96]);
% Get rid of tool bar and pulldown menus that are along top of figure.
% set(gcf, 'Toolbar', 'none', 'Menu', 'none');
% Give a name to the title bar.
set(gcf, 'Name', 'Demo by ImageAnalyst', 'NumberTitle', 'Off')

MATLAB: One image 2 diferent colors ,

It looks like B was simply the convolution of A with a high pass filter, like the Laplacian or dog filter. Do you want to do that or you simply want the black surround to be gray?

Best Answer

Related Solutions

MATLAB: Error using .* Integers can only be combined with integers of the same class, or scalar doubles.

MATLAB: One image 2 diferent colors ,

Related Question