Image segmentation depending on Delta E vlaue (Image analyst demo )

I have two groups of image,first group contains clear edges,and the second group doesn't have clear edges ,and I have two segmentation algorithms for each Images group so what I want to do:
1-If the image contains edge use the first segmentation algorithm
2-Else run the second segmentation algorithm,How can I do this procedure depending on the value of deltaE? (please find attached file for main_function,LocalDeltaE) this first sample image below
has clear edges,so I'll use the first segmentation algorithm(I have it's code),where the second image below has no clear edges so I'll the second segmentation algorithm
clear edges image is below
non-clear edges image is below
and the codes which I tried (depending on Image Analyst LocalDeltaE function ) are attached here[decision_value] = LocalDeltaE();

Answers (2)

That's a very slowly varying, smooth image. Chances are you didn't use a large enough window. Using 5 like in the demo is only good for fairly sharp edges. You might need 31 or 51 or something.

8 Comments

Thank you Dr.Image Analyst,I attached .m files,what I tried, could you review and correct them please,thanks in advance
Or if you have a time,please could you adapt your demo to my situation .
hi image analyst how can i ask you an image processing problem in private? thanks in advance
I have a gig at fiverr but I think here is best.
hi image analyst i have two images. The first image is original image and the second is the image resulted from 3d volume projection. How can i enhance second image for further processing like vessel extraction to get the result similar to that of the original image. The two images are attached here. thanks in advance
The images cannot be displayed. Try it and see. Please try again.
Hi again the links of images are added here.
https://drive.google.com/open?id=1e2LJqCjFqb_qbYw3mP9hN8lrBrwWU4wQ
https://drive.google.com/open?id=1RX2HQtPc1Tt7o7pYMRv6c9jiDzma8WOr
Since this has nothing to do with hamed's original question, please start your own discussion.

Sign in to comment.

Asked:

on 19 Jan 2014

Commented:

on 17 May 2018

Community Treasure Hunt

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

Start Hunting!