Home > Code > Kohonen Self-Organizing Map Demos

Kohonen Self-Organizing Map Demos

December 5th, 2005 shyam Leave a comment Go to comments

In artificial intelligence, SOMs, or Self-Organizing Maps, are a type of neural network. They can be used to ‘teach’ a computer to recognize various attributes. This project deals with two demos: SOM_Color and SOM_Image. Both are written in C#.

SOM_Color is a color recognition program. A grid of nodes is initialized with random colors. The application learns how the colors are related to each other, and will sort the colors so that like-colors end up near each other. Color “similarity” is defined by their respective RGB color vector Euclidean distance.

SOM_Image is an image recognition program. A database of images is presented to the application (Madden NFL ’06 images are provided with the download). The program will group similar images near each other. Two classifications are used for this similarity calculation: a histogram of lights/darks and colors. This application works surprisingly well.

There is also a paper that goes along with this project, to better explain the utilized techniques.

Download: source

Categories: Code Tags: , , ,
  1. Tim
    March 6th, 2009 at 05:54 | #1

    Hi,
    Is there a mirror for the download of these programs? Unfortunately, I get a 404 error when trying to download the bin + source.
    Thanks

  2. March 6th, 2009 at 13:48 | #2

    Sorry about the dead link. This section of the webpage is not linked from the main page, so I didn’t think it was actually active. I guess google must have picked it up.

    I just sent a download link to your provided email address. Enjoy.

  3. R Stone
    March 31st, 2009 at 11:07 | #3

    Hi. Would it be possible to email me the download link? I’m new to SOMs but there aren’t too many demo’s out in C#. Thank you.

  4. March 31st, 2009 at 12:13 | #4

    Download fixed.

  1. No trackbacks yet.