Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Practical view on face presentation attack detection

: Damer, Naser; Dimitrov, Kristiyan

Volltext (PDF; )

Wilson, R.C. ; The British Machine Vision Association and Society for Pattern Recognition (BMVA):
British Machine Vision Conference, BMVC 2016. Proceedings. Online resource : 19-22 September 2016, York, UK
Edinburgh: BMVA, 2016
11 S.
British Machine Vision Conference (BMVC) <27, 2016, York>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IGD ()
biometrics; spoofing attacks; liveness detection; Guiding Theme: Smart City; Research Area: Computer vision (CV); Research Area: Human computer interaction (HCI); CRISP

Face recognition is one of the most socially accepted forms of biometric recognition. The recent availability of very accurate and efficient face recognition algorithms leaves the vulnerability to presentation attacks as the major challenge to face recognition solutions. Previous works have shown high preforming presentation attack detection PAD solutions under controlled evaluation scenarios.
This work tried to analyze the practical use of PAD by investigating the more realistic scenario of cross-database evaluation and presenting a state-of-the-art performance comparison. The work also investigated the relation between the video duration and the PAD performance. This is done along with presenting an optical flow based approach that proves to outperform state-of-the-art solutions in most experiment settings.