Reducing the type II error rate in face recognition.
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
Get the accuracy of recognition, and if it's below a threshold - reject.
Would that work for you?