On the Robustness of Deep Learning Based Face Recognition

Abstract

Identifying persons using face recognition is an important task in applications such as media production, archiving and monitoring. Like other tasks, also face recognition pipelines have recently shifted to Deep Convolutional Neural Network (DNNs) based approaches. While they show impressive performance on standard benchmark datasets, the same performance is not always reached on real data from media applications. In this paper we address robustness issues in a face detection and recognition pipeline. First, we analyze the impact of image impairments (in particular compression) on face detection, and how to conceal them in order to improve face detection performance. This is studied both on face samples originating from still image and video data. Second, we propose approaches to improve open-set face recognition, i.e., handling of "unknown'' persons, in particular to reduce false positive recognitions. We provide experimental results on image and video data and provide conclusions that help to improve the performance in practical applications.