I was wondering if you can use the face detection opencv sample code and slot in a new xml file trainied to recognise the object you wanted it to.
would this work?
if not how do you do it, I have looked a few sites mainly site where it seems to suggest that its done somehow along those lines but I can't seem to get it to work, so was wondering if it is possible.
sure, that's possible.
the cascade classifier just finds, what the cascade-file was trained on, be it faces, eyes or soda-cans.
lots of existing examples here , and ofc, you can train your own, opencv comes with tools for that ( cascade_training, haar_training )