Reducing the type II error rate in face recognition.

asked 2014-05-02 08:56:24 -0500

ddabloch gravatar image

updated 2014-05-02 09:15:58 -0500

berak gravatar image

Does anyone have some insight as to how to reduce the type II error rate to a very low rate, even at the expense of increasing the type I error rate?

In other words, we want to make sure an imposter would not be recognized as an authorized user even if we end up rejecting a high percentage of authorized user.

Thanks for any help/idea

edit retag flag offensive close merge delete

Comments

Get the accuracy of recognition, and if it's below a threshold - reject.

Would that work for you?

GilLevi gravatar imageGilLevi ( 2014-05-03 14:29:44 -0500 )edit