MATLAB Answers

Color image segmentation using K-Means

Asked by Sabarinathan Vadivelu on 25 Aug 2012

The Example for Color image segmentation which I was found here Here. In this example they have segmented the blue color. Is there any example to segment only the red color or green color?

  1 Comment

RGB color are referred as 1,2,3. where 3 stands for blue color. So, in the same code modify the value of 3 as 2 to get green color and change the value as 1 to get red color.



No products are associated with this question.

1 Answer

Answer by Image Analyst
on 25 Aug 2012
 Accepted answer

I think you don't understand how k-means works. You specify k. In the example they specified 3 because they thought there should be, or wanted to be, 3 classes. Those three classes were magenta, blue, and white for that particular image. For your image they might be something different, say yellow, green, and cyan - it all depends on the content of the image. If your image has only two main colors, red and green, then maybe you should specify a k of 2 and it will find those two colors. Feel free to upload your image to the website of your choice if you want us to look at it.


Laila Hayat
on 27 Nov 2012

i have the same problem image is onion.png n i have to segment out 5 colors bt i didnt understand how to work on this

Image Analyst
on 27 Nov 2012

Can't you follow the example? Just change 3 to 5 and let it run. I can't try it because I don't have the Statistical Toolbox.

Discover MakerZone

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

Learn more

Discover what MATLAB® can do for your career.

Opportunities for recent engineering grads.

Apply Today

MATLAB Academy

New to MATLAB?

Learn MATLAB today!