Synthetic data model shows promise for biometric bias mitigation

The limitations of real-world biometric training datasets, including the introduction of bias through unbalanced demographic representation, are well established. Synthetic training data offers promise, but has its own limitations. A novel method of avoiding those limitations was presented at the Norwegian Biometrics Laboratory Annual Workshop 2024, hosted by the EAB earlier this month.

Pietro Melzi of the Autonomous University of Madrid presented the GANDiffFace model, which generates synthetic faces for the purpose of mitigating demographic bias in training data. …

bias biometric biometric-bias biometric r&d biometrics biometrics news biometrics research data data model datasets demographic fairness eab european association for biometrics facial recognition introduction limitations mitigation novel own real representation secunet synthetic synthetic data synthetic faces training training data workshop world