Investigating fairness of ocular biometrics among young, middle-aged, and older adults

Loading...
Thumbnail Image
Authors
Krishnan, Anoop
Almadan, Ali
Rattani, Ajita
Advisors
Issue Date
2021-10-11
Type
Conference paper
Preprint
Keywords
Fairness and bias in AI , Ocular biometrics , Agegroups , Deep learning , XAI
Research Projects
Organizational Units
Journal Issue
Citation
A. Krishnan, A. Almadan and A. Rattani, "Investigating Fairness of Ocular Biometrics Among Young, Middle-Aged, and Older Adults," 2021 International Carnahan Conference on Security Technology (ICCST), 2021, pp. 1-7, doi: 10.1109/ICCST49569.2021.9717383.
Abstract

A number of studies suggest bias of the face biometrics, i.e., face recognition and soft-biometric estimation methods, across gender, race, and age-groups. There is a recent urge to investigate the bias of different biometric modalities toward the deployment of fair and trustworthy biometric solutions. Ocular biometrics has obtained increased attention from academia and industry due to its high accuracy, security, privacy, and ease of use in mobile devices. A recent study in 2020 also suggested the fairness of ocular-based user recognition across males and females. This paper aims to evaluate the fairness of ocular biometrics in the visible spectrum among age-groups; young, middle, and older adults. Thanks to the availability of the latest large-scale 2020 UFPR ocular biometric dataset, with subjects acquired in the age range 18 - 79 years, to facilitate this study. Experimental results suggest the overall equivalent performance of ocular biometrics across gender and agegroups in user verification and gender-classification. Performance difference for older adults at lower false match rate and young adults was noted at user verification and age-classification, respectively. This could be attributed to inherent characteristics of the biometric data from these age-groups impacting specific applications, which suggest a need for advancement in sensor technology and software solutions.

Table of Contents
Description
Preprint from arXiv. This conference paper is also available the DOI link (may not be free).
Publisher
IEEE
Journal
Book Title
Series
2021 International Carnahan Conference on Security Technology (ICCST);2021
PubMed ID
DOI
ISSN
2153-0742
1071-6572
EISSN