Can the False Acceptance Rate (FAR) and False Rejection Rate (FRR) be adjusted for different use cases?

Yes. FaceMe offers recognition models with different accuracy levels and an adjustable matching threshold, allowing customers to achieve an appropriate balance between the False Acceptance Rate (FAR) and False Rejection Rate (FRR) based on their security requirements and use case.

For example, high-security applications such as access control or financial identity verification may use a stricter matching threshold, while convenience-oriented applications such as time and attendance can use different settings based on operational requirements.

We recommend testing under actual operating conditions during the POC stage to determine the appropriate recognition model and matching threshold.