A Study on the Impact of Face Image Quality on Face Recognition in the Wild

TL;DR

This paper investigates how face image quality affects face recognition performance in unconstrained environments, revealing that quality issues remain challenging for deep learning methods and humans excel in cross-quality face verification.

Contribution

It evaluates deep learning face recognition across different quality levels and compares human and machine performance, highlighting the ongoing importance of face image quality.

Findings

Deep learning performance drops with lower quality images

Humans outperform deep learning in cross-quality face verification

Face quality remains a significant challenge for current methods

Abstract

Deep learning has received increasing interests in face recognition recently. Large quantities of deep learning methods have been proposed to handle various problems appeared in face recognition. Quite a lot deep methods claimed that they have gained or even surpassed human-level face verification performance in certain databases. As we know, face image quality poses a great challenge to traditional face recognition methods, e.g. model-driven methods with hand-crafted features. However, a little research focus on the impact of face image quality on deep learning methods, and even human performance. Therefore, we raise a question: Is face image quality still one of the challenges for deep learning based face recognition, especially in unconstrained condition. Based on this, we further investigate this problem on human level. In this paper, we partition face images into three different quality sets to evaluate the performance of deep learning methods on cross-quality face images in the wild, and then design a human face verification experiment on these cross-quality data. The result indicates that quality issue still needs to be studied thoroughly in deep learning, human own better capability in building the relations between different face images with large quality gaps, and saying deep learning method surpasses human-level is too optimistic.