According to Microsoft's website, there are 3 measurements that represent the accuracy of Windows Hello's facial recognition, which are: False Positives; True Positives; and False Negatives. These are explained in the quote below
Microsoft represents the accuracy of Windows Hello face in three main
measures, which are: False Positives, True Positives, and False
Negatives.
False positives:
Also called False Acceptance Rate, represents the likelihood a random
user who obtains access to your device will be recognized as you. This
number should be as low as possible.
With windows 10, the results are less than 0.001% or 1/100,000 FAR
(False Acceptance Rate)
True Positives:
The True Positive rate represents the likelihood a user will be
correctly matched to their profile each time they are registered by
the camera This number should be high
The results with windows 10 are greater than 95% with a single
enrolled user
False negatives:
Represents the likelihood a user is not matched to their enrolled
profile. This number should be low.
The results with Windows 10 are less than 5% with a single enrolled
user.