Load Google Translate Well, I am pretty sure I can't give you a good answer, but I do remember doing some study of image / pattern recognition at Uni in the Robotics lectures. I remembered vaguely something about edge detection, but then I had to go googling
.
I suppose the short answer is, you do a lot of work developing algorithms capable of analysing an image, identifying edges and shapes and then correlating the identified shapes to shapes you're looking for and end up with some statistical likelyhood that the shape probably is or probably isn't a hand.
As for a normal web cam, well it's just that image capture device, it never knows if it's a hand or not, it's the thing that processes the image that has the smarts, the camera used just effects the maximum quality of the image that can be captured.
© 2009 Premier Farnell plc. All Rights Reserved
Premier Farnell plc, registered in England and Wales (no 00876412), registered office: Farnell House, Forge Lane, Leeds LS12 2NE