Just how much time do you spend at your local convenience store, mall or downtown street corner? Well, if Carnegie Mellon can do face recognition with Kirk, Spock, McCoy et al on the entire Star Trek The Original Series, then Pittsburgh Pattern Recognition can do it anywhere.
Here's a sample of face mining on the Enterprise; the fun starts at about 30 seconds in.
(Face Mining the enterprise)
Here we illustrate the face mining concept for the TV series Star Trek. Specifically, we applied our state-of-the art algorithms in face detection, face tracking and face recognition to 67 Star Trek episodes over three seasons. This process automatically extracts all visible face tracks, and clusters these into a small number of same-person groupings. Currently, we recognize frontal or near-frontal tracks. In the near future, we will extend our results to non-frontal tracks as well.
Given our face mining output, it took a person less than five minutes to assign names to all the main characters (Kirk, Spock, Mccoy, Uhura, Scotty, Sulu and Chekov) and a couple of minor ones (Janice, Nurse Chapel) across all 67 episodes.
(PittPatt Star Trek face recognition examples)
Before this miracle of computing, I relied on nerds (and, yes, my own dim recollection of those black-and-white, broadcast TV days) for ST:TOS knowledge. Now, though, we can go straight to the computers.
It should be clear that if Pittsburgh Pattern Recognition can do this with Star Trek footage, they should be able to do it with convenience store CCTV footage, mall CCTV footage, downtown street corner CCTV footage, and so forth. Of course, your favorite brand name corporations will already be presenting you with relevant advertisements on every flat surface, thanks to companies like Quividi, who determine your physical characteristics via face recognition.