[Yetanfou]

Facial recognition is a software function which can be performed on image data coming from any camera with sufficient resolution, most likely that includes the majority of surveillance cameras deployed in China. China might suffer under an antiquated and corrupt political system but the country does not lack modern technology.

[myself248]

Furthermore, facial recognition is constantly improving, and a camera that might've been inadequate for it a few years ago can now be used for matching, if not training.

Combine that with the replacement rate of cameras, and you get two factors crossing each other and meaning that the vast majority of those 200M cameras can already be used for recognition, and the ones that can't today, will be soon.

[davidhyde]

My point was not about what China is doing and what they are capable of. My point is that the reporting is shoddy.

You simply cannot recognise someone’s face in a large crowd with a traditional wide angle 320x240 resolution cctv camera mounted high up on a pole. This is not the movies where you can “zoom in and clarify”. Traditional cctv can place people at a certain time based on the colour of their clothes, their height etc. It is used for gathering evidence after a crime has been committed, not for automatically recognising people.

Modern cctv has high enough resolution for facial recognition but nobody bothers reporting numbers properly. It’s the differentiation between the capabilities that I want to point out. It’s like saying that there are 1 bn toy guns AND real guns in existence. It’s a meaningless number.

[fireattack]

Of course I don't have a number or source either, but it's not really that common to have such low resolution camera even for surveillance any more. At least not in China.