Click here to Skip to main content
15,936,709 members
Please Sign up or sign in to vote.
0.00/5 (No votes)
See more:
Hi, I want to segment an Image using SOM. I have no idea of how the input vectors are generated. I understand I need to extract that from image pixels, my question is how do I designate the pixel's class?Manually?
By the way,sorry for my poor English.
Updated 2-Nov-10 4:15am

1 solution


Which tool are you using? The way to input changes by the library you are using.

Generally and most simply, there is an Nx3 matrix, defining the feature vectors, such as:

R1 G1 B1
R2 G2 B2
Rn Gn Bn

The result will be an Nx1 vector, a class label for all the pixels.

This method is not limited to SOMs. It's valid for many unsupervised classifiers such as GMMs etc.

Share this answer

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)

CodeProject, 20 Bay Street, 11th Floor Toronto, Ontario, Canada M5J 2N8 +1 (416) 849-8900