SoylentNews is people
SoylentNews
from the false-positives-are-a-bad-thing-said-one-of-the-twins dept.
If you've watched any sort of spy thriller or action film over the last few years – think Jason Bourne or Mission: Impossible – the chances are you've seen facial recognition software in action. These movie scenes often involve an artist's sketch compared to mug shots, or sometimes even a live CCTV stream, and with the clock ticking, a match is usually found for the culprit in the nick of time.
It seems natural then to assume that what happens in the film world is similar to what happens (most of the time) in the real world. We might think that our faces are constantly being tracked and recognised as we walk past security cameras in city centres – but this is not actually the case.
Not only would such a system require millions of cameras capable of producing high-quality footage, but it would also require the integration of photo-ID databases such as mugshots from every police force, previous passport images, and driving license images for everyone in the country.
And yet even if this high level of integration was possible, a far more basic problem still exists – facial recognition systems are still not 100% accurate.
(Score: 1, Interesting) by Anonymous Coward on Friday December 16 2016, @04:14PM
It only needs one or two breakthroughs to go from 75 percent to 90+ percent positive rate. I imagine all those 'neural networks' and similiar science fields are working furiously to solve exactly this problem, along with dozens of others.
And related to that: There were 50 megapixel CCDs a number of years ago that Nokia bought up exclusive production rights to for the high end lumia windows phones they produced, just before that microsoft guy took them over then ruined them. I've mentioned this in a couple other threads in the past: Where did all those 50MP CCD units go? And given how underpowered the phones they were built into were, how much more dangerous would those CCDs be if they had for instance been surplused into the hands of a government (European, American, or British) who might be using those units right now to generate real time views of an area for priming a real time facial recognition system backed with a neural network implementation.
The only thing that had been stopping this from happening prior to this point in time was bandwidth, storage, and processing limitations. All of which have after a few year lull suddenly begun ramping up in performance/capacity again, suspiciously right as pro-authoritarian shifts in government have become more prevalent...