1
$\begingroup$

i have been segmented some image of retina. but the result is not good as i hope. for one image i can get good segmentation, like this image image with good segmentation

image with bad segmentation

my code is from some reference in internet, in below i will write my code and this code is start when i have got a filtered image (mean filtering) .

prewitthor = [-1 0 1; -1 0 1; -1 0 1]; 
prewittver = [-1 -1 -1; 0 0 0; 1 1 1]; 
Ix = imfilter(double(imgMeanfilter),prewitthor,'replicate'); 
Iy = imfilter(double(imgMeanfilter),prewittver,'replicate');
J = sqrt((Ix.^2)+(Iy.^2)); 
g = J - min(J(:));
g = g / max(g(:));

th = graythresh(g); %# Otsu's method.
a = imhmax(g,th/2); %# Conservatively remove local maxima.
th = graythresh(a);
b = a > th/4; %# Conservative global threshold.
c = imclose(b,ones(3)); %# Try to close contours.
d = imfill(c,'holes'); %# Not a bad segmentation by itself.
%# Use the rough segmentation to define markers.
%  g2 = imimposemin(g, ~ imdilate( bwperim(a), ones(3) ));
L = watershed(c);
boundaries = L == 0;
redChanel(boundaries) = 255;
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.