Fusion Methods for Face Presentation Attack Detection
Face presentation attacks (PA) are a serious threat to face recognition (FR) applications. These attacks are easy to execute and difficult to detect. An attack can be carried out simply by presenting a video, photo, or mask to the camera. The literature shows that both modern, pre-trained, deep lear...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/14/5196 |
| _version_ | 1797433096612610048 |
|---|---|
| author | Faseela Abdullakutty Pamela Johnston Eyad Elyan |
| author_facet | Faseela Abdullakutty Pamela Johnston Eyad Elyan |
| author_sort | Faseela Abdullakutty |
| collection | DOAJ |
| description | Face presentation attacks (PA) are a serious threat to face recognition (FR) applications. These attacks are easy to execute and difficult to detect. An attack can be carried out simply by presenting a video, photo, or mask to the camera. The literature shows that both modern, pre-trained, deep learning-based methods, and traditional hand-crafted, feature-engineered methods have been effective in detecting PAs. However, the question remains as to whether features learned in existing, deep neural networks sufficiently encompass traditional, low-level features in order to achieve optimal performance on PA detection tasks. In this paper, we present a simple feature-fusion method that integrates features extracted by using pre-trained, deep learning models with more traditional colour and texture features. Extensive experiments clearly show the benefit of enriching the feature space to improve detection rates by using three common public datasets, namely CASIA, Replay Attack, and SiW. This work opens future research to improve face presentation attack detection by exploring new characterizing features and fusion strategies. |
| first_indexed | 2024-03-09T10:12:16Z |
| format | Article |
| id | doaj.art-274e5200bd67409b827f64b001d36f3b |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T10:12:16Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-274e5200bd67409b827f64b001d36f3b2023-12-01T22:39:59ZengMDPI AGSensors1424-82202022-07-012214519610.3390/s22145196Fusion Methods for Face Presentation Attack DetectionFaseela Abdullakutty0Pamela Johnston1Eyad Elyan2School of Computing, Robert Gordon University, Aberdeen AB10 7AQ, UKSchool of Computing, Robert Gordon University, Aberdeen AB10 7AQ, UKSchool of Computing, Robert Gordon University, Aberdeen AB10 7AQ, UKFace presentation attacks (PA) are a serious threat to face recognition (FR) applications. These attacks are easy to execute and difficult to detect. An attack can be carried out simply by presenting a video, photo, or mask to the camera. The literature shows that both modern, pre-trained, deep learning-based methods, and traditional hand-crafted, feature-engineered methods have been effective in detecting PAs. However, the question remains as to whether features learned in existing, deep neural networks sufficiently encompass traditional, low-level features in order to achieve optimal performance on PA detection tasks. In this paper, we present a simple feature-fusion method that integrates features extracted by using pre-trained, deep learning models with more traditional colour and texture features. Extensive experiments clearly show the benefit of enriching the feature space to improve detection rates by using three common public datasets, namely CASIA, Replay Attack, and SiW. This work opens future research to improve face presentation attack detection by exploring new characterizing features and fusion strategies.https://www.mdpi.com/1424-8220/22/14/5196face presentation attacksdeep learningfeature-fusion |
| spellingShingle | Faseela Abdullakutty Pamela Johnston Eyad Elyan Fusion Methods for Face Presentation Attack Detection Sensors face presentation attacks deep learning feature-fusion |
| title | Fusion Methods for Face Presentation Attack Detection |
| title_full | Fusion Methods for Face Presentation Attack Detection |
| title_fullStr | Fusion Methods for Face Presentation Attack Detection |
| title_full_unstemmed | Fusion Methods for Face Presentation Attack Detection |
| title_short | Fusion Methods for Face Presentation Attack Detection |
| title_sort | fusion methods for face presentation attack detection |
| topic | face presentation attacks deep learning feature-fusion |
| url | https://www.mdpi.com/1424-8220/22/14/5196 |
| work_keys_str_mv | AT faseelaabdullakutty fusionmethodsforfacepresentationattackdetection AT pamelajohnston fusionmethodsforfacepresentationattackdetection AT eyadelyan fusionmethodsforfacepresentationattackdetection |