Face Biometrics – Better Accuracy Across Races, Genders

A sampling of commercial facial recognition algorithms seems to suggest that face biometrics systems are currently too dependent on certain attributes to differentiate as easily between different people who share race and gender categories. A paper explores the issue with five unnamed commercial facial recognition algorithms, with a commercial iris recognition algorithm as a control.

The paper suggests that those facial recognition algorithms searching large databases of homogenous images tend to result in disparate treatment based on race and gender. Analysis of the principal components used by the biometrics algorithms shows that most variations between vectors, or facial appearance, are not related to race or gender, though around 10 percent do. This means that it should be possible for the face biometrics algorithms to more consistently avoid delivering unfair accuracy differentials.

Further, the separation between mated and non-mated score distributions reconstructed exclusively using principal components that do not cluster individuals by race and gender was only modestly reduced, suggesting CFRAs (commercial facial recognition algorithms) can maintain acceptable performance even when ignoring face features associated with race and gender.

Read more