Key points are not available for this paper at this time.
Soft biometrics enable the identification of subjects based on semantic descriptions collected from eye-witnesses allowing people to search in surveillance databases. Although research has recently shown an increased interest in soft biometrics, not much of the work have used crowdsourcing, and it did not investigate the impact of feature selection on identification. In this paper, we introduce a new set of facial soft biometrics and labels with a novel description for the eyebrow region. Also, we examine the use of crowdsourcing for labelling the comparative facial soft biometrics and assess its impact on the identification. Moreover, we explore the impact of feature selection with our biometric measures and evaluate the effect of label scale compression. Experiments based on the Southampton biometric tunnel database demonstrate a 100% rank-1 identification rate using 20 features only.
Almudhahka et al. (Mon,) studied this question.