get the x,y coordinate of the boundaries of the entities in the attached image. I have written the code to do so but still not able to get the co-ordinate because not able to get the continuous curve.

blood = imread('boundaries.jpg');
[x,y]=size(blood);                
b=double(blood);                  
N =sqrt(100) * randn(x,y);        
I=b+N;                           

for i=1:x                        
    for j=1:y
        if (I(i,j)>255)
            I(i,j)=255;
        end
        if (I(i,j)<0)
            I(i,j)=0;
        end
    end
end    

z0=max(max(I));                  
z1=min(min(I));                   

T=(z0+z1)/2;                      
TT=0;
S0=0; n0=0;
S1=0; n1=0;
allow=0.5;                       
d=abs(T-TT);
count=0;                        

while(d>=allow)                 
    count=count+1;
    for i=1:x
        for j=1:y
            if (I(i,j)>=T)
                S0=S0+I(i,j);
                n0=n0+1;
            end
            if (I(i,j)<T)
                S1=S1+I(i,j);
                n1=n1+1;
            end
        end
    end 
    T0=S0/n0;
    T1=S1/n1;
    TT=(T0+T1)/2;
    d=abs(T-TT);
    T=TT;
end

Seg=zeros(x,y);
for i=1:x
    for j=1:y
        if(I(i,j)>=T)
            Seg(i,j)=1;              
        end
    end
end

SI=1-Seg;                            
se1=strel('square',3);               
SI1=imerode(SI,se1);                 
BW=SI-SI1;                          
I=uint8(I);

figure(1);

imshow(BW);title('New algorithm')

[Image Analyst]

That code is not good. Like I said below, use bwboundaries. Simple extract the green channel, threshold, and call bwboundaries. If you want the boundaries as an image instead of an N-by-2 list of (x,y) coordinates, then call bwperim(). But don't do it the way you did.

Answer 1

[Image Analyst]

Simply use bwboundaries(). See this code snippet from my Image Processing Tutorial in my File Exchange:

% bwboundaries() returns a cell array, where each cell contains the row/column coordinates for an object in the image.
% Plot the borders of all the coins on the original grayscale image using the coordinates returned by bwboundaries.
subplot(3, 3, 6);
imshow(originalImage);
title('Outlines, from bwboundaries()', 'FontSize', captionFontSize); 
axis image; % Make sure image is not artificially stretched because of screen's aspect ratio.
hold on;
boundaries = bwboundaries(binaryImage);
numberOfBoundaries = size(boundaries, 1);
for k = 1 : numberOfBoundaries
  thisBoundary = boundaries{k};
  plot(thisBoundary(:,2), thisBoundary(:,1), 'g', 'LineWidth', 2);
end
hold off;