I'd like to distinguish different types of beers in my fridge using a Raspberry Pi. I saw a very good tutorial on Adafruit that utilized OpenCV for face recognition. Can these same face recognition algorithms, Eigenfaces & Fisherfaces, be used to train my raspberry pi for recognizing different types of beer cans?
Not being an expert, I would guess that face recognition algorithms are way to specialized and heavy to do this. They will try to identify a "face" first of all - two eyes and a nose and a mouth and so on - and then try to identify them based on a set of parameters that can be detected in that face.
I think you would be a lot better off using some kind of optical character recognition (OCR) software, or simply sample the colour and draw wild conclusions from there.
Since the RPi now comes with Mathematica, we can use its image processing functionality to analyze beer labels. The folks at Mathematica.SE have performed a similar task with Jelly jars (apparently Mathematica users are teatotalers).
I have not tried the operations above on an RPi; however assuming there are no problems with limited memory or excessive image processing time, using an RPi with this process is in principle the same.