I suspect the claimed “99.98% accuracy” is counting out of all faces scanned, which is a bullshit way to make the tech look good. Most faces are not marked as shoplifters in the database. A system that literally does nothing would probably still have greater than 99% accuracy.
What we really want to know is what percentage of reported matches are accurate, and I bet it isn’t anywhere near 99%.
I had to try to educate sales people what such numbers actually mean.
With fingerprint readers, there are false positives (your finger is accepted, although it should not), and false negatives (your finger gets rejected although it should accept). The chances for both look small, but if you have 700+ people in the system, the chance of a random person to be accepted as one of the 700 is about bigger than 50%. And there was a big chance for any valid user to be logged in as someone else.
Yes, it was intended to be used for identification and authentification in one go. For something between 500 to 700 people, and the customer wanted it to work with dirty or injured fingers, too, so the readers would have to be extraordinarily lenient.
My guess is that the customer watched too many movies.
I suspect the claimed “99.98% accuracy” is counting out of all faces scanned, which is a bullshit way to make the tech look good. Most faces are not marked as shoplifters in the database. A system that literally does nothing would probably still have greater than 99% accuracy.
What we really want to know is what percentage of reported matches are accurate, and I bet it isn’t anywhere near 99%.
I had to try to educate sales people what such numbers actually mean.
With fingerprint readers, there are false positives (your finger is accepted, although it should not), and false negatives (your finger gets rejected although it should accept). The chances for both look small, but if you have 700+ people in the system, the chance of a random person to be accepted as one of the 700 is about bigger than 50%. And there was a big chance for any valid user to be logged in as someone else.
Pretty much this. A 0.02% error margin when there are tens of thousands of visitors per year, means it’s almost guaranteed to have errors.
99.9% ^700 = 49.6% chance of no errors occurring.
99.98% ^3466 = 50% chance of no errors occurring.
99.98% ^23000 = 1% chance of no errors occurring.
Pretty much that. The customer wanted to use it for identification and authentification in one go, with lenience for dirty and injured fingers on top.
Fingerprints as username??
Yes, it was intended to be used for identification and authentification in one go. For something between 500 to 700 people, and the customer wanted it to work with dirty or injured fingers, too, so the readers would have to be extraordinarily lenient.
My guess is that the customer watched too many movies.