Fix Matlab Filter Error: Pseudo Inverse Filter for Image Restoration

[jerin_007]

Homework Statement

I am doing a project on mathematical analysis of image restoration techniques, using linear restoration filters such as
1.inverse filter
2.pseudo inverse filter
3.weiner filter and
4.constrained least square filter

Homework Equations

The Attempt at a Solution

For the pseudo inverse filter, I've programmed as following:

clc;
clear all;
close all;
f=imread('C:\Documents and Settings\Jerin\Desktop\lenna.gif');
PSF=fspecial('motion', 14,0);
gb=imfilter(f,PSF);
g=imnoise (gb,'gaussian',0,200/(255*255));
fr=deconvwnr (g,PSF);
k=fft(fr);
for i=1:1:150;
H=pfilter('ideal',size(fr,1),size(fr,2),i);
G=H.*k;
g1=real(ifft2(G));
g1=g1(1:size(fr,1),1:size(fr,2));
e=double (f)-double(g1);
[m,n]=size(e);
rmse(i)=sqrt(sum(e(:).^2)/(m*n));
end;
i=1:1:150;
figure(2);
plot(i,rmse(i));

Now i am getting an error like this:

The output should be like this:

If posssible, guys please copy the program and work it out in MATLAB for the correct output, i know you can sort it out very easily. Please its urgent.

What filter i should use? is the pfilter correct? I got this programmed from a friend.

 

[KataKoniK]

Hi there,

It seems like you are trying to implement the pseudo inverse filter in MATLAB for image restoration. From the code you have provided, it looks like you are on the right track. However, there are a few things that could be causing the error you are getting.

Firstly, make sure that all necessary variables are defined and initialized before running the code. For example, the variables "f" (input image), "PSF" (point spread function), and "g" (noisy blurred image) should all be defined and initialized before using them in the code.

Secondly, it is important to check the size of the images and filters being used. Make sure that the size of the PSF and the input image are compatible with the size of the filter being used (in this case, the "pfilter" function). If they are not compatible, you may get an error like the one you are getting.

Lastly, it is always a good idea to break down your code into smaller parts and test each part separately to identify where the error is coming from. This will help you in troubleshooting and finding the correct solution.

As for your question about which filter to use, it ultimately depends on your specific project and the type of image restoration you are trying to achieve. Each filter has its own advantages and limitations, so it is important to understand them and choose the one that best suits your needs.

I hope this helps and good luck with your project!