Oh, it's really, really fast. My current system is based upon two generations back of neural nets, and they reconstruct from one photo in 0.9 seconds. The latest generation does 144 reconstructions simultaneously given HD video feeds.
BTW, all the best with your website. Hope you take more avatars "where go where no man has gone before!"
Just beware of Bonferroni's Principle:
http://math.stackexchange.com/questions/352689/bonferronis-p...
They might find hundreds of pictures of you with timestamps and locations.
(This is all speculation; I haven't written image recognition software myself.)
http://www.cs.cmu.edu/~vboddeti/papers/ijcb_2011.pdf
I have two more in the pipe (one still awaiting acceptance, and the other is accepted but yet to be added to IEEEXplore)