converting boundary to mask

lets assume that this is the code i used to identify the boundary. I want display the selected boundary in new window else convert this to mask. is it possible.. some one please help me

I = imread('F:\project_matlab\dataset\002.jpg');

BW = im2bw(I, graythresh(I));

[B,L] = bwboundaries(BW,'noholes');

imshow(label2rgb(L, @jet, [.5 .5 .5]))

hold on

for k = 1:length(B)

    boundary = B{k};

   plot(boundary(:,2), boundary(:,1), 'w', 'LineWidth', 2)

end

Answer 1

[Dishant Arora]

b=bwboundaries(BW);   % BW being your binary image
mask=false(size(BW));
for i = 1:length(b)
    for j = 1:length(b{i})
        ind = b{i}(j,:);
        mask(ind(1),ind(2))=1;
    end
end
figure
imshow(mask)

[Ibrahim Thorig]

Dear;

Actually I am trying plot this mask in new window. but when i try your method it shows me whole image. i don't want see back ground. I only need the mask area.

thanks for the help

[Image Analyst]

But you have both the binary image and the boundaries. I don't know what you want. If you don't want the "whole image" then what do you want? Dishant's code basically does the same as bwperim() - it gives you an image where the boundaries are white/true/1 and the rest is black/false/0. Can you post an image showing what you want in this "mask area"? Again, the mask area is the same as the binary image, what you call BW, so do you want just one blob out of a group of blobs that define your mask?

[Ibrahim Thorig]

dear; actually i want extract image from this image.

[Dishant Arora]

BW = imfill(BW , 'holes')  % will give you desired mask

[Image Analyst]

No need to get boundaries on that image. Simply threshold. The it depends on what you mean by "extract". What does that mean to you? To you mean crop? Do you want the white bar along the bottom of the image also to be included? What about the white torn edge? It can go from simple to complex depending on exactly what you want to do and what kind of images the algorithm can be expected to encounter.