Edge detection using Fuzzy Logic

I am trying to detect edge of gray scale image using fuzzy logic. In my code first I am trying to detect edge and then to remove noise. Edge detection part is working,but noise removal part have not worked. Edge detection pixels have values between 0 to 50 and background pixel values have constant value i.e. 128. In case of noise removal I put if else conditions . But each checked pixel i.e. z(i,j) satisfies only if condition whether it is true or not. Following is my code.........
a=imread('a.jpg');
g1=rgb2gray(a);
g=imresize(g1,[200 200]);
[m,n]=size(g);
%figure, imshow(g)
%edge detection part
t=readfis('edge.fis');
z=uint8(zeros(m,n));
for i=2:m-1
for j=2:n-1
F = [g(i-1,j-1) g(i-1,j) g(i,j-1) g(i,j)];
h=double(F);
z(i,j)=evalfis(h,t);
end
end
disp(z)
figure, imshow(z)
%noise removal part
z2=uint8(zeros(m,n));
for i=2:m-1
for j=2:n-1
if ((0<=z(i-1,j-1)<=50) & (0<=z(i-1,j)<=50) & (0<=z(i-1,j+1)<=50) & (0<=z(i,j-1)<=50) & (0<=z(i,j)<=50) & (0<=z(i,j+1)<=50) & (0<=z(i+1,j-1)<=50) & (0<=z(i+1,j)<=50) & (0<=z(i+1,j+1)<=50))
% if z1(i-1,j-1)==0 && z1(i-1,j)==0 && z1(i-1,j+1)==0 && z1(i,j-1)==0 && z1(i,j)==0 && z1(i,j+1)==0 && z1(i+1,j-1)==0 && z1(i+1,j)==0 && z1(i+1,j+1)==0
z2(i,j)=128;
else
z2(i,j)=z(i,j);
end
end
end
figure, imshow(z2)

2 Comments

hi Res,
I cant help you but i need ur help. i also want to do edge detection with fuzzy logic. but i don't know how to start. can you please suggest me something for writing fuzzy logic code.
Thanks in advance
i need edge detection using fuzzy

Sign in to comment.

Answers (3)

Omid Sarrafzadeh
Omid Sarrafzadeh on 30 Jul 2012
Hi Res It depends on your 'edge.fis' FIS and your rules. May I know more about them?

1 Comment

Hi Res, Can u explain what is 'edge.fis'.

Sign in to comment.

hamed Aghapanah
hamed Aghapanah on 4 Oct 2019
Dear Res,
I do it and ind that there are many solution to find edge. Because the result is related to Membership Functions.
which one is the best solution?
thanks

Categories

Find more on Fuzzy Logic Toolbox in Help Center and File Exchange

Asked:

Res
on 21 May 2012

Answered:

on 4 Oct 2019

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!