Face presentation attack detection. A comprehensive evaluation of the generalisation problem
Abstract Face recognition technology is now mature enough to reach commercial products, such as smart phones or tablets. However, it still needs to increase robustness against imposter attacks. In this regard, face Presentation Attack Detection (face‐PAD) is a key component in providing trustable fa...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-07-01
|
| Series: | IET Biometrics |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/bme2.12049 |
| _version_ | 1826831867113897984 |
|---|---|
| author | Artur Costa‐Pazo Daniel Pérez‐Cabo David Jiménez‐Cabello José Luis Alba‐Castro Esteban Vazquez‐Fernandez |
| author_facet | Artur Costa‐Pazo Daniel Pérez‐Cabo David Jiménez‐Cabello José Luis Alba‐Castro Esteban Vazquez‐Fernandez |
| author_sort | Artur Costa‐Pazo |
| collection | DOAJ |
| description | Abstract Face recognition technology is now mature enough to reach commercial products, such as smart phones or tablets. However, it still needs to increase robustness against imposter attacks. In this regard, face Presentation Attack Detection (face‐PAD) is a key component in providing trustable facial access to digital devices. Despite the success of several face‐PAD works in publicly available datasets, most of them fail to reach the market, revealing the lack of evaluation frameworks that represent realistic settings. Here, an extensive analysis of the generalisation problem in face‐PAD is provided, jointly with an evaluation strategy based on the aggregation of most publicly available datasets and a set of novel protocols to cover the most realistic settings, including a novel demographic bias analysis. Besides, a new fine‐grained categorisation of presentation attacks and instruments is provided, enabling higher flexibility in assessing the generalisation of different algorithms under a common framework. As a result, GRAD‐GPAD v2, a comprehensive and modular framework is presented to evaluate the performance of face‐PAD approaches in realistic settings, enabling accountability and fair comparison of most face‐PAD approaches in the literature. |
| first_indexed | 2024-03-09T09:32:59Z |
| format | Article |
| id | doaj.art-7826e036a1454342a7d4ae16210cb2ce |
| institution | Directory Open Access Journal |
| issn | 2047-4938 2047-4946 |
| language | English |
| last_indexed | 2025-02-16T10:07:15Z |
| publishDate | 2021-07-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Biometrics |
| spelling | doaj.art-7826e036a1454342a7d4ae16210cb2ce2025-02-03T01:29:37ZengWileyIET Biometrics2047-49382047-49462021-07-0110440842910.1049/bme2.12049Face presentation attack detection. A comprehensive evaluation of the generalisation problemArtur Costa‐Pazo0Daniel Pérez‐Cabo1David Jiménez‐Cabello2José Luis Alba‐Castro3Esteban Vazquez‐Fernandez4Alice Biometrics Vigo SpainAlice Biometrics Vigo SpainR&D Nielsen IQ Madrid SpainatlanTTic research center at University of Vigo Vigo SpainAlice Biometrics Vigo SpainAbstract Face recognition technology is now mature enough to reach commercial products, such as smart phones or tablets. However, it still needs to increase robustness against imposter attacks. In this regard, face Presentation Attack Detection (face‐PAD) is a key component in providing trustable facial access to digital devices. Despite the success of several face‐PAD works in publicly available datasets, most of them fail to reach the market, revealing the lack of evaluation frameworks that represent realistic settings. Here, an extensive analysis of the generalisation problem in face‐PAD is provided, jointly with an evaluation strategy based on the aggregation of most publicly available datasets and a set of novel protocols to cover the most realistic settings, including a novel demographic bias analysis. Besides, a new fine‐grained categorisation of presentation attacks and instruments is provided, enabling higher flexibility in assessing the generalisation of different algorithms under a common framework. As a result, GRAD‐GPAD v2, a comprehensive and modular framework is presented to evaluate the performance of face‐PAD approaches in realistic settings, enabling accountability and fair comparison of most face‐PAD approaches in the literature.https://doi.org/10.1049/bme2.12049face recognitionpose estimationvideo signal processingobject tracking |
| spellingShingle | Artur Costa‐Pazo Daniel Pérez‐Cabo David Jiménez‐Cabello José Luis Alba‐Castro Esteban Vazquez‐Fernandez Face presentation attack detection. A comprehensive evaluation of the generalisation problem IET Biometrics face recognition pose estimation video signal processing object tracking |
| title | Face presentation attack detection. A comprehensive evaluation of the generalisation problem |
| title_full | Face presentation attack detection. A comprehensive evaluation of the generalisation problem |
| title_fullStr | Face presentation attack detection. A comprehensive evaluation of the generalisation problem |
| title_full_unstemmed | Face presentation attack detection. A comprehensive evaluation of the generalisation problem |
| title_short | Face presentation attack detection. A comprehensive evaluation of the generalisation problem |
| title_sort | face presentation attack detection a comprehensive evaluation of the generalisation problem |
| topic | face recognition pose estimation video signal processing object tracking |
| url | https://doi.org/10.1049/bme2.12049 |
| work_keys_str_mv | AT arturcostapazo facepresentationattackdetectionacomprehensiveevaluationofthegeneralisationproblem AT danielperezcabo facepresentationattackdetectionacomprehensiveevaluationofthegeneralisationproblem AT davidjimenezcabello facepresentationattackdetectionacomprehensiveevaluationofthegeneralisationproblem AT joseluisalbacastro facepresentationattackdetectionacomprehensiveevaluationofthegeneralisationproblem AT estebanvazquezfernandez facepresentationattackdetectionacomprehensiveevaluationofthegeneralisationproblem |