Can Shadows Reveal Biometric Information?

TL;DR

This paper investigates how shadows can leak biometric information, demonstrating that shadows can be used to reliably infer identities through a novel learning-based approach that leverages synthetic data and domain adaptation.

Contribution

It introduces a new method for biometric inference from shadows using synthetic data and unsupervised domain adaptation, without requiring labeled real data.

Findings

High accuracy in identity classification from shadows

Effective generalization to real-world scenes

Robustness to scene variations

Abstract

We study the problem of extracting biometric information of individuals by looking at shadows of objects cast on diffuse surfaces. We show that the biometric information leakage from shadows can be sufficient for reliable identity inference under representative scenarios via a maximum likelihood analysis. We then develop a learning-based method that demonstrates this phenomenon in real settings, exploiting the subtle cues in the shadows that are the source of the leakage without requiring any labeled real data. In particular, our approach relies on building synthetic scenes composed of 3D face models obtained from a single photograph of each identity. We transfer what we learn from the synthetic data to the real data using domain adaptation in a completely unsupervised way. Our model is able to generalize well to the real domain and is robust to several variations in the scenes. We report high classification accuracies in an identity classification task that takes place in a scene with unknown geometry and occluding objects.