The crossover error rate (CER) is a measure of the performance of a biometric system, such as a fingerprint scanner or facial recognition system. It is the point at which the false accept rate (FAR) and the false reject rate (FRR) are equal and is often used as a benchmark for evaluating the accuracy of biometric systems.
The false accept rate (FAR) is the probability that a biometric system will incorrectly match an input to a reference in the system, while the false reject rate (FRR) is the probability that a biometric system will incorrectly reject a valid input. The CER is the point at which the FAR and FRR are equal and is typically expressed as a percentage.
For example, if a biometric system has a FAR of 1% and a FRR of 1%, its CER would be 1%. This would indicate that the system is performing at an acceptable level of accuracy, as both the FAR and FRR are low.
Overall, the CER is an important measure of the performance of biometric systems and is used to evaluate the accuracy and reliability of these systems. It is often used as a benchmark for comparing the performance of different biometric systems.