[depth concept] · introduction of EER (equal error rate)

· Introduction of the evaluation index EER(Equal Error Rate)
In-depth learning articles generally use Error probabilities such as EER(Equal Error Rate) as an objective criterion for measuring classifiers, and the RECEIVER Operating Characteristic (ROC) curve explains how to calculate EER.
Here is a brief introduction to the EER calculation
EER (Average error probability) is a biometric security system algorithm used to pre-determine its error acceptance rate and its error rejection rate threshold. When the rates are equal, the common value is called the equal error rate. This value indicates that the proportion of false acceptances is equal to the proportion of false rejections. The lower the iso-error rate, the higher the accuracy of biometric identification system.
 

 
Use other ROC evaluation criteria
AUC (area under thecurve), also is the area under the ROC curve, the greater the classifier, the better, the maximum value is 1, the blue stripes in the graph area is the blue curve corresponding AUCEER (equal error rate), that is, the value of the FPR = FNR, due to the FNR = 1 – TPR, can draw A from (0, 1) to (1, 0) in A straight line, finding the intersection point, in the figure A and B two points.

Read More: