5

enter image description here

I have a vein image as follow. I use watershed algorithm to extract the skeleton of the vein.

My code: (K is the original image).

level = graythresh(K);
BW = im2bw(K,level);
D = bwdist(~BW);
DL = watershed(D);
bgm = DL == 0;
imshow(bgm);

The result is:

enter image description here

As you can see lot of information is lost. Can anybody help me out? Thanks.

W00f
  • 137
  • 2
  • 9

3 Answers3

8

It looks like the lighting is somewhat uneven. This can be corrected using certain morphological operations. The basic idea is to compute an image that represents just the uneven lighting and subtract it, or to divide by it (which also enhances contrast). Because we want to find just the lighting, it is important to use a large enough structuring element, so that the operation examines more global properties rather than local ones.

%# Load image and convert to [0,1].
A = im2double(imread('https://i.stack.imgur.com/TQp1i.png'));
%# Any large (relative to objects) structuring element will do.
%# Try sizes up to about half of the image size.
se = strel('square',32);
%# Removes uneven lighting and enhances contrast.
B = imdivide(A,imclose(A,se));
%# Otsu's method works well now.
C = B > graythresh(B);
D = bwdist(~C);
DL = watershed(D);
imshow(DL==0);

Here are C (left), plus DL==0 (center) and its overlay on the original image:

Divided by closing Otsu's method Segmentation overlay

reve_etrange
  • 2,561
  • 1
  • 22
  • 36
  • Works well. Pictures would be nice, though. – Jonas Apr 16 '12 at 03:31
  • Thank you very much for your help. Just one quick question. If I want to apply imopen followed by imclose should I just edit this part se = strel('square',32); im_open = imopen(A,se); B = imdivide(A,imclose(im_open,se)); Im the paper that I am reading right now, they said using this way could help much in reducing the false branches. However when I did in this way there seems to be more false branches lol. Do you have any suggestion? Thanks – W00f Apr 16 '12 at 16:37
  • The image I was using is here http://img534.imageshack.us/img534/8876/testrlt.png – W00f Apr 16 '12 at 16:47
  • They are probably talking about using the opened/closed image directly, not dividing by it. See [here](http://www.mathworks.com/products/image/demos.html?file=/products/demos/shipping/images/ipexwatershed.html) for more information on this technique. The idea is to make regions more homogeneous. – reve_etrange Apr 16 '12 at 19:36
  • Try using a larger structuring element, like `64` instead of `32`. Which size works best will be determined by the size of the heterogeneous parts of the image. – reve_etrange Apr 16 '12 at 19:45
1

Yes, you'll need to lower your threshold likely (lower than what Otsu's method is giving you). And if the edge map is noisy when you lower the threshold, you should apply a 2-D Gaussian smoothing filter before you lower the threshold. This will move the edges slightly but will clean up noise too, so it's a tradeoff.

The 2-D Gaussian can be applied doing something like

w=gausswin(N,Alpha)  % you'll have to play with N and alpha
K = imfilter(K,w,'same','symmetric'); % something like these options

Before you apply the rest of your algorithm.

Chris A.
  • 6,817
  • 2
  • 25
  • 43
1

You are losing information because when you apply im2bw, you are basically converting your uint8 image, where the pixel brightness takes a value from intmin('uint8')==0 to intmax('uint8')==255, into a binary image (where only logical values are used). This is what entails a loss of information that you observed. If you display the image BW you will see that all the elements of K that had a value greater than the threshold level turn into ones, while those ones below the threshold turn into zeros.

Drodbar
  • 539
  • 5
  • 14