Child Face Recognition at Scale: Synthetic Data Generation and Performance Benchmark

TL;DR

This paper introduces HDA-SynChildFaces, a large synthetic dataset of children's faces generated using GANs and face aging models, and evaluates facial recognition performance and biases across age groups and races.

Contribution

The paper presents a novel pipeline for generating a large, balanced, and varied synthetic dataset of children's faces using GANs and face age progression models.

Findings

Children's face recognition performance is worse than adults and declines with age.

Recognition systems exhibit biases against Asian, Black, female, and minority race subjects.

The dataset enables comprehensive benchmarking of face recognition systems on children.

Abstract

We address the need for a large-scale database of children's faces by using generative adversarial networks (GANs) and face age progression (FAP) models to synthesize a realistic dataset referred to as HDA-SynChildFaces. To this end, we proposed a processing pipeline that initially utilizes StyleGAN3 to sample adult subjects, which are subsequently progressed to children of varying ages using InterFaceGAN. Intra-subject variations, such as facial expression and pose, are created by further manipulating the subjects in their latent space. Additionally, the presented pipeline allows to evenly distribute the races of subjects, allowing to generate a balanced and fair dataset with respect to race distribution. The created HDA-SynChildFaces consists of 1,652 subjects and a total of 188,832 images, each subject being present at various ages and with many different intra-subject variations. Subsequently, we evaluates the performance of various facial recognition systems on the generated database and compare the results of adults and children at different ages. The study reveals that children consistently perform worse than adults, on all tested systems, and the degradation in performance is proportional to age. Additionally, our study uncovers some biases in the recognition systems, with Asian and Black subjects and females performing worse than White and Latino Hispanic subjects and males.