• search hit 6 of 116
Back to Result List

Child face recognition at scale: synthetic data generation and performance benchmark

  • 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”. Hence, we proposed a processing pipeline that initially utilizes StyleGAN3 to sample adult subjects, which is 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, this pipeline allows the even distribution of the races of subjects, allowing the generation of a balanced and fair dataset with respect to race distribution. The resulting HDA-SynChildFaces consists of 1,652 subjects and 188,328 images, each subject being present at various ages and with many different intra-subject variations. We then evaluated the performance of various facial recognition systems on the generated database and compared the results of adults and children at different ages. The study reveals that children consistently perform worse than adults on all tested systems and that 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.

Download full text files

Export metadata

Additional Services

Share in Twitter Search Google Scholar       frontdoor_oas    
Metadaten
Author:Magnus Falkenberg, Anders Bensen Ottsen, Mathias Ibsen, Christian Rathgeb
URN:urn:nbn:de:hebis:ds114-opus4-4385
DOI:https://doi.org/10.3389/frsip.2024.1308505
ISSN:2673-8198
Parent Title (English):Frontiers in Signal Processing
Publisher:Frontiers Media S.A.
Place of publication:Lausanne
Document Type:Article
Language:English
Year of Completion:2024
Publishing Institution:Hochschule Darmstadt
Release Date:2024/06/04
Tag:biometrics; children; face recognition; generative adversarial networks; synthetic data
GND Keyword:-
Volume:4
Page Number:17
Note:
Originalveröffentlichung: Falkenberg M, Bensen Ottsen A, Ibsen M and
Rathgeb C (2024), Child face recognition at scale: synthetic data generation and performance benchmark. Front. Sig. Proc. 4:1308505.
doi: 10.3389/frsip.2024.1308505
Institutes:Informatik
OpenAIRE:OpenAIRE
Licence (German):License LogoCreative Commons - CC BY - Namensnennung 4.0 International