I do not understand this relationship.

According to wikipedia, the CER can easily be obtained from the ROC curve.

Equal error rate or crossover error rate (EER or CER): the rate at which both acceptance and rejection errors are equal. The value of the EER can be easily obtained from the ROC curve. The EER is a quick way to compare the accuracy of devices with different ROC curves. In general, the device with the lowest EER is the most accurate.

However, the ROC and CER curves are clearly very different: ROC ROC

and CER:


How is the Cross Over Error rate "easily obtained" from the ROC curve? Or rather, what is the quantitative relationship between these?

It might be worth mentioning that my application is not for biometrics, but it is a binary classifier. Thanks

  • 1
    $\begingroup$ Hi. I cannot believe your question still exists, for over five years and there is no answer. I have got the same problem. Have you found anything instructive on that? Cheers! $\endgroup$ – Celdor Dec 1 '15 at 11:56
  • $\begingroup$ Unfortunately, not. The question has only existed since July 10th of this year. Please upvote to give it more attention! $\endgroup$ – Sother Dec 21 '15 at 17:42
  • 1
    $\begingroup$ I have got date wrong :p $\endgroup$ – Celdor Dec 23 '15 at 11:16

Your Answer

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

Browse other questions tagged or ask your own question.