how can i extract blood vessels from a noisy image?

hello sir..I want to extract a blood vessel from a noisy image.I want only the vessel part of the image. i have attached my images. can somebody help me please.
Thanks in advance!! and thanks a ton for all response that u guys had given me!!! uu all guys have helped me a lot thanks again
sir, i want to remove the background i mean to say the white part of inside retina...how can i do it
and i want my output image to look

5 Comments

hello vidya ... please tell me which filter u applied for extracting the blood vessels..?
gabor filter sir..actually i did not extract vessels till now..i just have my image in convoluted form
can u pl. send the code u hv used to get the o/p vein image..
You might try Firefox - it has a built in spell checker.
ANJU
ANJU on 2 Dec 2013
Edited: ANJU on 2 Dec 2013
please tell me did u enhance the vessels before extraction ??

Sign in to comment.

 Accepted Answer

This is not so trivial. It's not like simple global or adaptive thresholding will robustly work for all images, though if you're lucky it may work for some normal (non-pathological) images. I recommend you find a suitable algorithm in section 20.5 here: http://iris.usc.edu/Vision-Notes/bibliography/contentsmedical.html#Medical%20Applications,%20CAT,%20MRI,%20Ultrasound,%20Heart%20Models,%20Brain%20Models Pick one, then code it up. If you need help with MATLAB code after that, contact us again.

3 Comments

yes sir..is that possible to blur the background and keep only the foreground vessel part.I just want the back ground(white and black color) to be removed and only vessels to remain..is it not possible my any enhancement of by background removal technique
Sure, you can do that in two lines of code. Just make up a kernel with a positive central weight and negative outer weights and call imfilter or conv2():
kernel = [-1, -1, -1; -1, 8, -1; -1, -1, -1]; % 3 by 3 window.
unsharpMaskedImage = imfilter(grayImage, kernel);
thank u so much sir..Now its quite better..

Sign in to comment.

Categories

Community Treasure Hunt

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

Start Hunting!