Analysing Comparative Soft Biometrics from Crowdsourced Annotations

What is it about?

Soft biometrics enable human description and identification from low quality surveillance footage. This paper premises the design, collection and analysis of a novel crowdsourced dataset of comparative soft biometric body annotations, obtained from a richly diverse set of human annotators.

Featured Image

Why is it important?

We include gender as a comparative trait and we find that comparative labels characteristically contain additional discriminative information over traditional categorical annotations. Our approach can reliably return the correct match in the the top 7% of results with 10 comparisons, or top 13% of results using just 5 sets of subject comparisons.