Face Verification Using 60~GHz 802.11 waveforms

TL;DR

This paper explores face verification using 60 GHz 802.11 waveforms, leveraging mmWave radar signatures and a novel dataset, with preliminary promising results using autoencoders.

Contribution

It introduces a new approach for face verification using 60 GHz 802.11 waveforms and demonstrates initial success with autoencoders on a novel dataset.

Findings

Promising initial results with autoencoders for face verification

Successful collection of a 200-person face dataset using mmWave radar

Feasibility of using 802.11ad/y hardware for biometric verification

Abstract

Verification of an identity based on the human face radar signature in mmwave is studied. The chipset for 802.11ad/y networking that is cable of operating in a radar mode is used. A dataset with faces of 200 different persons was collected for the testing. Our preliminary study shows promising results for the application of autoencoder for the setup at hand.