Face Recognition In Children: A Longitudinal Study

TL;DR

This study introduces the YFA dataset to evaluate children's face recognition over short age gaps, revealing a significant decline in match scores with increasing age difference but also demonstrating promising accuracy for age gaps up to three years.

Contribution

The paper presents the first longitudinal children's face dataset and analyzes face recognition performance over short age gaps, highlighting the impact of age and sample quality.

Findings

Significant score decay with increasing age-gap in children.

Face recognition achieves over 94% TAR at 0.1% FAR for 36-month age gaps.

Face recognition performance is feasible for children up to three years age difference.

Abstract

The lack of high fidelity and publicly available longitudinal children face datasets is one of the main limiting factors in the development of face recognition systems for children. In this work, we introduce the Young Face Aging (YFA) dataset for analyzing the performance of face recognition systems over short age-gaps in children. We expand previous work by comparing YFA with several publicly available cross-age adult datasets to quantify the effects of short age-gap in adults and children. Our analysis confirms a statistically significant and matcher independent decaying relationship between the match scores of ArcFace-Focal, MagFace, and Facenet matchers and the age-gap between the gallery and probe images in children, even at the short age-gap of 6 months. However, our result indicates that the low verification performance reported in previous work might be due to the intra-class structure of the matcher and the lower quality of the samples. Our experiment using YFA and a state-of-the-art, quality-aware face matcher (MagFace) indicates 98.3% and 94.9% TAR at 0.1% FAR over 6 and 36 Months age-gaps, respectively, suggesting that face recognition may be feasible for children for age-gaps of up to three years.