Practical View on Face Presentation Attack Detection

Naser Damer and Kristiyan Dimitrov

Abstract

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.

Session

Posters 2

Files

PDF iconExtended Abstract (PDF, 938K)
PDF iconPaper (PDF, 481K)

DOI

10.5244/C.30.112
https://dx.doi.org/10.5244/C.30.112

Citation

Naser Damer and Kristiyan Dimitrov. Practical View on Face Presentation Attack Detection. In Richard C. Wilson, Edwin R. Hancock and William A. P. Smith, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 112.1-112.11. BMVA Press, September 2016.

Bibtex

        @inproceedings{BMVC2016_112,
        	title={Practical View on Face Presentation Attack Detection},
        	author={Naser Damer and Kristiyan Dimitrov},
        	year={2016},
        	month={September},
        	pages={112.1-112.11},
        	articleno={112},
        	numpages={11},
        	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
        	publisher={BMVA Press},
        	editor={Richard C. Wilson, Edwin R. Hancock and William A. P. Smith},
        	doi={10.5244/C.30.112},
        	isbn={1-901725-59-6},
        	url={https://dx.doi.org/10.5244/C.30.112}
        }