Face Recognition Performance: Role of Demographic Information

Abstract

Abstract-This paper studies the influence of demographics on the performance of face recognition algorithms. The recognition accuracies of six different face recognition algorithms (three commercial, two non-trainable, and one trainable) are computed on a large scale gallery that is partitioned so that each partition consists entirely of specific demographic cohorts. Eight total cohorts are isolated based on gender (male and female), race/ethnicity (Black, White, and Hispanic), and age group (18 to 30, 30 to 50, and 50 to 70 years old). Experimental results demonstrate that both commercial and the non-trainable algorithms consistently have lower matching accuracies on the same cohorts (females, Blacks, and age group 18 to 30). Additional experiments investigate the impact of the demographic distribution in the training set on the performance of a trainable face recognition algorithm. We show that the matching accuracy for race/ethnicity and age cohorts can be improved by training exclusively on that specific cohort. Operationally, this leads to a scenario, called dynamic face matcher selection, where multiple face recognition algorithms (each trained on different demographic cohorts), are available for a biometric system operator to select based on the demographic information extracted from a probe image. This procedure should lead to improved face recognition accuracy in many intelligence and law enforcement face recognition scenarios.

How Does Aging Affect Facial Components?

“…Both our method and FaceVACS generally have higher accuracy on males than females, and higher accuracy on whites and Hispanics than blacks. These results are consistent with the results reported in [24], and with most algorithms evaluated in [25]. There are a couple of exceptions to these trends, on the 0-1 year age gap FaceVACS is slightly more accurate on black females than black males, while on the 5-10 year age gap our method has higher accuracy for black females than white females.…”

“…Figure 3 shows the stages of our component localization process, which is essentially the same as the one described in [19]. We start by aligning all face images based on their eye locations, which we detect using the FaceVACS SDK [24].…”

Assemblage of the vertical: commercial drones and algorithmic life

“…According to recent studies, algorithmic biometrics exhibit demonstrable racial bias (Angwin et al, 2016;Klare et al, 2012). In one case, an algorithm in use in police departments in multiple US states failed twice as often with African American subjects as with Caucasian subjects (Klare et al, 2012). Facial detection, tracking and recognition is fast becoming a significant factor in security discourses.…”

Open source biometric recognition

“…The default face recognition algorithm in OpenBR is based on the Spectrally Sampled Structural Subspaces Features (4SF) algorithm [11]. 4SF is a statistical learningbased algorithm used previously to study the impact of demographics [12] and aging [13] on face recognition performance.…”