If you have difficulty in submitting comments on draft standards you can use a commenting template and email it to admin.start@bsigroup.com. The commenting template can be found here.
This document establishes applicability evaluation methodology for synthetic biometric samples in biometric performance testing. It also defines report requirements to ensure transparency regarding the synthetic biometric samples used. This document only treats with synthesizing biometric samples generated from real biometric samples, with trying to keep respective identities of the latter biometric samples. The testing targets are image-based modalities including, but not to limited to face, fingerprint and vein.
Specifically, this document:
- defines applicability evaluation methodology focusing on (1) quality of the synthetic biometric samples and (2) score similarity between real and synthetic biometric samples.
- specifies report contents to ensure transparency through results.
This document does not:
- specify image synthesis techniques or algorithms.
- cover synthetic biometric samples not generated from real biometric samples.
- address biometric performance testing methodologies beyond the use of synthetic biometric samples as defined within this scope.
- establish specific performance thresholds or acceptance criteria for biometric systems.
Biometric technology is increasingly prevalent in diverse applications, including access control, identification, and personalization across various sectors such as offices, transportation hubs, retail, healthcare, and entertainment. This widespread adoption necessitates robust and cost-effective methods for performance testing that reflect real-world use cases. Traditional biometric performance testing relies heavily on the collection of real biometric data, which can be expensive and timeconsuming. Consequently, the use of synthetic images for performance testing has emerged as a promising solution to address these challenges. However, a significant gap exists in the standardization of what types of synthetic samples are applicable to such evaluations. Therefore, there is a critical need for standardization concerning the applicability evaluation of synthetic samples as outlined in the scope of this proposed standard.
Required form fields are indicated by an asterisk (*) character.
You are now following this standard. Weekly digest emails will be sent to update you on the following activities:
You can manage your follow preferences from your Account. Please check your mailbox junk folder if you don't receive the weekly email.
You have successfully unsubscribed from weekly updates for this standard.
Comment by: