Skip to main content

Research Repository

Advanced Search

Deep transfer learning on the aggregated dataset for face presentation attack detection.

Abdullakutty, Faseela; Elyan, Eyad; Johnston, Pamela; Ali-Gombe, Adamu

Authors

Adamu Ali-Gombe



Abstract

Presentation attacks are becoming a serious threat to one of the most common biometric applications, namely face recognition (FR). In recent years, numerous methods have been presented to detect and identify these attacks using publicly available datasets. However, such datasets are often collected in controlled environments and are focused on one specific type of attack. We hypothesise that a model's accurate performance on one or more public datasets does not necessarily guarantee generalisation across other, unseen face presentation attacks. To verify our hypothesis, in this paper, we present an experimental framework where the generalisation ability of pre-trained deep models is assessed using four popular and commonly used public datasets. Extensive experiments were carried out using various combinations of these datasets. Results show that, in some circumstances, a slight improvement in model performance can be achieved by combining different datasets for training purposes. However, even with a combination of public datasets, models still could not be trained to generalise to unseen attacks. Moreover, models could not necessarily generalise to a learned format of attack over different datasets. The work and results presented in this paper suggest that more diverse datasets are needed to drive this research as well as the need for devising new methods capable of extracting spoof-specific features which are independent of specific datasets.

Citation

ABDULLAKUTTY, F., ELYAN, E., JOHNSTON, P. and ALI-GOMBE, A. 2022. Deep transfer learning on the aggregated dataset for face presentation attack detection. Cognitive computation [online], 14(6), pages 2223-2233. Available from: https://doi.org/10.1007/s12559-022-10037-z

Journal Article Type Article
Acceptance Date Jun 30, 2022
Online Publication Date Jul 7, 2022
Publication Date Nov 30, 2022
Deposit Date Jul 15, 2022
Publicly Available Date Mar 29, 2024
Journal Cognitive computation
Print ISSN 1866-9956
Electronic ISSN 1866-9964
Publisher Springer
Peer Reviewed Peer Reviewed
Volume 14
Issue 6
Pages 2223-2233
DOI https://doi.org/10.1007/s12559-022-10037-z
Keywords Presentation attack detection; Data aggregation; Unseen attacks
Public URL https://rgu-repository.worktribe.com/output/1699431

Files




You might also like



Downloadable Citations