Windows 10 mobile devices, Surface Laptops, and several other 3rd parties integrate an Intel Realsense 3D camera.

Windows Hello extends this 3D camera to support user authentication.

  • What security parameters are used to describe the relative security of this authentication? (for example, fingerprint readers use quantity of points to determine the integrity of the scan)

  • What other relevant information is useful for comparing this biometric authentication

  • 1
    Since you cannot change biometric parameters (e.g. your face!), I personally think that biometric logins can only ever be a convenience feature not really a security one. Certainly not a high-security feature. Well managed multi-factor authentication will always be stronger. However, for many use cases, it is going to be "good enough" Sep 12, 2016 at 9:12
  • @JulianKnight This question is regarding the technical quality of the biometric data received. I'm looking for a summary of data points, class, resolution, vertices, etc that are used for this feature. Sep 12, 2016 at 14:23
  • ... also not authentication is the same. Windows Hello implies "something you have", which is the computer with the non-transferrable hello data. Akin to the thumbprint sensor on many devices. You do have valid points though. Sep 12, 2016 at 14:25
  • "This question is regarding" - Yes, that's why that is a comment and not an answer. ;-) Sep 12, 2016 at 14:26
  • Is the hello data non-transferable? I've not checked whether it syncs to other machines along with much other data. Good point though. Sep 12, 2016 at 14:27

1 Answer 1


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.

  • 1
    this is a generic description of biometrics in general, none of this answers the question
    – schroeder
    May 1, 2017 at 6:48

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.