Image recognition to extract various shapes from screen

Question

0.00/5 (No votes)

See more:

Hi all,

I have an idea that I want to put in practice and don't know where to start with documentation.

The same way photo cameras can recognize face, I want to create a tool that recognize train tracks from Google maps, Yahoo maps, .. so on. The source doesn't matter, it should be some mathematics involved for sure.

Some satelitte images are not clear enough and my software will need to put the pieces together even for blured/shaded portions of the tracks.
Some facts are to be useful such as train tracks are most of the time paralel to each other, track points usualy have the same shape (especially in a sorting yard it's highly possible that all points have the same radius).
Just as for train modelling, there are predefined track portions with already known length and radius so the software should go through available shapes and return the best match.

Any ideas are welcomed. Once again, I am posting here in order to narrow the search for the right techniques for image recognition, shape matching or what ever should be called that applies to my problem.

Thanks a million,
Dani

Posted 2-Jun-13 3:20am

Dobre Dani

Add a Solution

1 solution

Add a Solution

Add your solution here

Treat my content as plain text, not as HTML

Preview 0

…

Existing Members

Sign in to your account

...or Join us

Download, Vote, Comment, Publish.

Your Email
Password
Forgot your password?

Your Email
This email is in use. Do you need your password?
Optional Password

I have read and agree to the Terms of Service and Privacy Policy
Please subscribe me to the CodeProject newsletters

When answering a question please:

Read the question carefully.
Understand that English isn't everyone's first language so be lenient of bad spelling and grammar.
If a question is poorly phrased then either ask for clarification, ignore it, or edit the question and fix the problem. Insults are not welcome.
Don't tell someone to read the manual. Chances are they have and don't get it. Provide an answer or move on to the next question.

Let's work to help developers, not make them feel stupid.

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

Christian Graus · Answer 1 · 2013-06-02T03:46:00

Any image processing I've ever needed to do, I searched for SIGRAPH[^] as well as my search terms, and found a paper that explained the math, then I wrote the code from there. This is a pretty vague request, I'm not sure how much more anyone can help you, unless someone knows of an existing library. Face recognition is very possible, as you've seen, but it's not a trivial task.