You are reading a single comment by @Greasy_Slag and its replies.
Click here to read the full conversation.
London Fixed Gear and Single-Speed is a community of predominantly fixed gear and single-speed cyclists in and around London, UK.
This site is supported almost exclusively by donations. Please consider donating a small amount regularly.
@Greasy_Slag
ANPR as a pattern recognition is so much easier than facial recognition.
For facial recognition you need to take two distinct points (typically the eyes) and analyse the distance from those eyes to each of the key points on the face (chin, lips, nose, ears etc etc) then reduce these to vector points and find a matching pattern. it's very accurate needs a very good resolution to start with i.e US passport photos on entry... you know where they are going?!
Lucky for us the GVT find fining motorists for "crimes" such as speeding more important than violent street crime