views:

35

answers:

2

Hi guys.

Usually I develop image process or recognition program on windows. But I got a custom who requires me to implement one on Linux platform.

Because his platform is embedded system, I can not know for sure that OpenCV would be available. Could anyone give me some clue to get started?

+2  A: 

You can package OpenCV with your application.

The word 'embedded' makes me nervous - image recognition can be very computationally expensive. You may need to roll your own code to fit the target constraints.

The starting point of your own code is likely to implement a Haar-like recogniser. This is of course what you'd likely be using OpenCV to do. A more ambitious recogniser is HOG. Here's a nice comparison of them.

Will
Note that OpenCV can be tricky to build on anything other than x86 - it has a *lot* of dependencies (e.g. ffmpeg) and all these obviously need to build on your target platform. If the embedded system is something other than x86 then it may take significant time and effort to get OpenCV working.
Paul R
Thanks for your reply. My main concern is that OpenCV might not be easy to be port to the target platform. So I need some reference or documentation about the 'native' method to manipulate image and build every algorithm by myself.
MaoWoo
A: 

Adaboost should be a good fit for use as a learning algorithm. Paul Viola and Michael Jones have an interesting paper on efficient face detection using Adaboost and Haar classifiers. There's a lot of math there, but it's worth reading.

spyked