A Study on the Effect of Ageing in Facial Authentication and the Utility of Data Augmentation to Reduce Performance Bias Across Age Groups
This work presents a study on the effects of aging on the performance and reliability of facial authentication methods. First, a brief review of the literature on the effect of age on face recognition algorithms is presented, followed by a detailed description of the face aging datasets. In contrast...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10242105/ |
| _version_ | 1827818164324401152 |
|---|---|
| author | Wang Yao Muhammad Ali Farooq Joseph Lemley Peter Corcoran |
| author_facet | Wang Yao Muhammad Ali Farooq Joseph Lemley Peter Corcoran |
| author_sort | Wang Yao |
| collection | DOAJ |
| description | This work presents a study on the effects of aging on the performance and reliability of facial authentication methods. First, a brief review of the literature on the effect of age on face recognition algorithms is presented, followed by a detailed description of the face aging datasets. In contrast with some recent studies, we demonstrate significant variations in authentication robustness between age groups. The second part of this paper focuses on a comprehensive comparative assessment on the effects across age groups. Four different face recognition algorithms are studied of which three are state-of-the-art neural network based models and the fourth one is a conventional machine learning model. Two different age range threshold settings (±3 in Experiment Category A and ±5 in Experiment Category B) of the age groups are adopted in the experimental analysis to get a proper comparison. Moreover, a synthetic aging method has been incorporated to augment the age data. Experimental result shows that the older adults groups are easier to identify with higher levels of accuracy and robustness compared to other age groups, while younger adults are the most challenging and false authentications are more likely to occur. |
| first_indexed | 2024-03-12T00:44:02Z |
| format | Article |
| id | doaj.art-4c2dc7f302814df88b365b52e6c0680c |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-12T00:44:02Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-4c2dc7f302814df88b365b52e6c0680c2023-09-14T23:00:33ZengIEEEIEEE Access2169-35362023-01-0111971189713410.1109/ACCESS.2023.331261210242105A Study on the Effect of Ageing in Facial Authentication and the Utility of Data Augmentation to Reduce Performance Bias Across Age GroupsWang Yao0https://orcid.org/0000-0002-1014-2788Muhammad Ali Farooq1https://orcid.org/0000-0003-4116-8021Joseph Lemley2Peter Corcoran3https://orcid.org/0000-0003-1670-4793College of Science and Engineering, University of Galway, Galway, IrelandCollege of Science and Engineering, University of Galway, Galway, IrelandCollege of Science and Engineering, University of Galway, Galway, IrelandCollege of Science and Engineering, University of Galway, Galway, IrelandThis work presents a study on the effects of aging on the performance and reliability of facial authentication methods. First, a brief review of the literature on the effect of age on face recognition algorithms is presented, followed by a detailed description of the face aging datasets. In contrast with some recent studies, we demonstrate significant variations in authentication robustness between age groups. The second part of this paper focuses on a comprehensive comparative assessment on the effects across age groups. Four different face recognition algorithms are studied of which three are state-of-the-art neural network based models and the fourth one is a conventional machine learning model. Two different age range threshold settings (±3 in Experiment Category A and ±5 in Experiment Category B) of the age groups are adopted in the experimental analysis to get a proper comparison. Moreover, a synthetic aging method has been incorporated to augment the age data. Experimental result shows that the older adults groups are easier to identify with higher levels of accuracy and robustness compared to other age groups, while younger adults are the most challenging and false authentications are more likely to occur.https://ieeexplore.ieee.org/document/10242105/Age effectdata augmentationface recognitionFR evaluation |
| spellingShingle | Wang Yao Muhammad Ali Farooq Joseph Lemley Peter Corcoran A Study on the Effect of Ageing in Facial Authentication and the Utility of Data Augmentation to Reduce Performance Bias Across Age Groups IEEE Access Age effect data augmentation face recognition FR evaluation |
| title | A Study on the Effect of Ageing in Facial Authentication and the Utility of Data Augmentation to Reduce Performance Bias Across Age Groups |
| title_full | A Study on the Effect of Ageing in Facial Authentication and the Utility of Data Augmentation to Reduce Performance Bias Across Age Groups |
| title_fullStr | A Study on the Effect of Ageing in Facial Authentication and the Utility of Data Augmentation to Reduce Performance Bias Across Age Groups |
| title_full_unstemmed | A Study on the Effect of Ageing in Facial Authentication and the Utility of Data Augmentation to Reduce Performance Bias Across Age Groups |
| title_short | A Study on the Effect of Ageing in Facial Authentication and the Utility of Data Augmentation to Reduce Performance Bias Across Age Groups |
| title_sort | study on the effect of ageing in facial authentication and the utility of data augmentation to reduce performance bias across age groups |
| topic | Age effect data augmentation face recognition FR evaluation |
| url | https://ieeexplore.ieee.org/document/10242105/ |
| work_keys_str_mv | AT wangyao astudyontheeffectofageinginfacialauthenticationandtheutilityofdataaugmentationtoreduceperformancebiasacrossagegroups AT muhammadalifarooq astudyontheeffectofageinginfacialauthenticationandtheutilityofdataaugmentationtoreduceperformancebiasacrossagegroups AT josephlemley astudyontheeffectofageinginfacialauthenticationandtheutilityofdataaugmentationtoreduceperformancebiasacrossagegroups AT petercorcoran astudyontheeffectofageinginfacialauthenticationandtheutilityofdataaugmentationtoreduceperformancebiasacrossagegroups AT wangyao studyontheeffectofageinginfacialauthenticationandtheutilityofdataaugmentationtoreduceperformancebiasacrossagegroups AT muhammadalifarooq studyontheeffectofageinginfacialauthenticationandtheutilityofdataaugmentationtoreduceperformancebiasacrossagegroups AT josephlemley studyontheeffectofageinginfacialauthenticationandtheutilityofdataaugmentationtoreduceperformancebiasacrossagegroups AT petercorcoran studyontheeffectofageinginfacialauthenticationandtheutilityofdataaugmentationtoreduceperformancebiasacrossagegroups |