Decomposition of Image using dyadic wavelet transform

Hii, Can some one help me in providing code for decomposition of image using dyadic wavelet transform into LL and HH subbands.

Answer 1

[Prasanna]

Hi Nishtha,

Decomposition of image into LL and HH subbands can be done using the ‘dwt2’ function present in MATLAB. To perform the decomposition you can perform the following steps:

• Load the image.
• Convert the image to grayscale.
• Perform wavelet decomposition.
• Extract the LL and HH sub bands from the decomposition.

Below is a MATLAB example on how to perform a 2D wavelet decomposition using the ‘dwt2’ function. 

% load the image and convert it to grayscale 
image = imread('cameraman.tif'); 
grayImage = im2gray(image) 

% perform wavelet decomposition using the dwt2 function 
[LL1,LH1,HL1,HH1]=dwt2(grayImage,'db1'); 
[LL2,LH2,HL2,HH2]=dwt2(LL1,'db1'); 
[LL3,LH3,HL3,HH3]=dwt2(LL2,'db1'); 

% Display the original image and the subbands 
figure; 
subplot(1, 3, 1); 
imshow(image); 
title('Original Image'); 

subplot(1, 3, 2); 
imshow(LL1, []); 
title('LL Subband'); 


subplot(1, 3, 3); 
imshow(HH1, []); 
title('HH Subband'); 

The above code gives the following output:

For more information regarding the functions used and some other examples, you can refer to the following resources:

• dwt2: https://www.mathworks.com/help/wavelet/ref/dwt2.html
• LL,LH,HL,HH decomposition: https://www.mathworks.com/matlabcentral/answers/634054-what-are-ll-lh-hl-hh-in-dwt
• MATLAB code for third level DWT: https://www.mathworks.com/matlabcentral/answers/163844-how-to-write-matlab-code-for-third-level-dwt