Unconstrained Face Detection and Open-Set Face Recognition Challenge

TL;DR

This paper discusses the challenges of face detection and open-set face recognition in outdoor surveillance environments, highlighting current limitations and the need for further research.

Contribution

It introduces a new challenge focusing on unconstrained face detection and open-set recognition in surveillance settings, emphasizing the gap in current capabilities.

Findings

High detection rates achievable with moderate false accepts

Open-set face recognition remains significantly weak

Surveillance conditions pose unique challenges for face recognition

Abstract

Face detection and recognition benchmarks have shifted toward more difficult environments. The challenge presented in this paper addresses the next step in the direction of automatic detection and identification of people from outdoor surveillance cameras. While face detection has shown remarkable success in images collected from the web, surveillance cameras include more diverse occlusions, poses, weather conditions and image blur. Although face verification or closed-set face identification have surpassed human capabilities on some datasets, open-set identification is much more complex as it needs to reject both unknown identities and false accepts from the face detector. We show that unconstrained face detection can approach high detection rates albeit with moderate false accept rates. By contrast, open-set face recognition is currently weak and requires much more attention.