Got Questions? Get Answers.
Discover MakerZone

MATLAB and Simulink resources for Arduino, LEGO, and Raspberry Pi

Learn more

Discover what MATLAB® can do for your career.

Opportunities for recent engineering grads.

Apply Today

Thread Subject:
How to extract the area that i want by using Gray Level Co-occurrence matrix?

Subject: How to extract the area that i want by using Gray Level Co-occurrence matrix?

From: Bow

Date: 30 Dec, 2012 17:37:08

Message: 1 of 3

According to my image from the link below
http://pic.free.in.th/id/5e7749626ba6a7da01d3903d3d1b8be3

I want to detect the black dots between the red line which i think it'll be easier if i canextract those area first and i think using GLCM to define its texture will be the solution for this problem. But i can't figure out how to do this or any better solution?, please advice me. Thank you

Subject: How to extract the area that i want by using Gray Level Co-occurrence matrix?

From: Image Analyst

Date: 31 Dec, 2012 04:55:15

Message: 2 of 3

"Bow" wrote in message <kbpu44$qim$1@newscl01ah.mathworks.com>...
> According to my image from the link below
> http://pic.free.in.th/id/5e7749626ba6a7da01d3903d3d1b8be3
>
> I want to detect the black dots between the red line which i think it'll be easier if i canextract those area first and i think using GLCM to define its texture will be the solution for this problem. But i can't figure out how to do this or any better solution?, please advice me. Thank you

-----------------------------------------------------------------------------------
Bow:
I don't have a good intuitive idea for what GLCM should look like for images, so I tend not to use it. I would try more traditional methods first. if you want a texture filter you can try entropyfilt() or stdfilt(). If you know something about the location, like it's within 300 pixels of the outer boundary, then you can find the outer boundary or otherwise somehow locate where the black void zone should be. You probably could be able to simply use morphological methods like imopen() - that's what I'd probably try first - and then just threshold, maybe combine it with filtering based on size or location or something like that.
Image Analyst

Subject: How to extract the area that i want by using Gray Level Co-occurrence matrix?

From: Bow

Date: 31 Dec, 2012 06:35:12

Message: 3 of 3

"Image Analyst" wrote in message <kbr5rj$3d3$1@newscl01ah.mathworks.com>...
> "Bow" wrote in message <kbpu44$qim$1@newscl01ah.mathworks.com>...
> > According to my image from the link below
> > http://pic.free.in.th/id/5e7749626ba6a7da01d3903d3d1b8be3
> >
> > I want to detect the black dots between the red line which i think it'll be easier if i canextract those area first and i think using GLCM to define its texture will be the solution for this problem. But i can't figure out how to do this or any better solution?, please advice me. Thank you
>
> -----------------------------------------------------------------------------------
> Bow:
> I don't have a good intuitive idea for what GLCM should look like for images, so I tend not to use it. I would try more traditional methods first. if you want a texture filter you can try entropyfilt() or stdfilt(). If you know something about the location, like it's within 300 pixels of the outer boundary, then you can find the outer boundary or otherwise somehow locate where the black void zone should be. You probably could be able to simply use morphological methods like imopen() - that's what I'd probably try first - and then just threshold, maybe combine it with filtering based on size or location or something like that.
> Image Analyst
> -----------------------------------------------------------------------------------
Dear Image Analyst,
Thank you for your reply, I want to make it automatically which can detect it without fix the pixel or intensity because each image may not has the black area at same pixel. I alreay tried with entropyfilt and i'm not sure that is the correct way or not. I think i will use morphology for sure but i think i will use after extract that area.

Tags for this Thread

What are tags?

A tag is like a keyword or category label associated with each thread. Tags make it easier for you to find threads of interest.

Anyone can tag a thread. Tags are public and visible to everyone.

Contact us