BROWSE
Detail
Conference Paper
A Background Analysis Technique for Video Liveness Detection
Cited - time in 
Share 
Share
- Authors
- Young Whan Kim, Soon Young Park, Jang-Hee Yoo, Ki-Young Moon, Kyoung Ho Choi
- Issue Date
- 2010-02
- Citation
- Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV) 2010, pp.418-421
- Language
- English
- Type
- Conference Paper
- Abstract
- Biometric face recognition systems are getting popular for various applications such as access control, human computer interfaces, surveillance, and so on. For those systems, a robust “liveness detection” scheme is required to prevent from using a copy of biometric information. In this paper, a novel fake detection approach is presented for biometric face recognition systems using background analysis. More specifically, a video spoofing attack is detected 1) by analyzing motion information of the background region and 2) by comparing the similarity of current background region and the original background region that was stored at the initializing stage. Experimental results show that the proposed approach is very promising for various spoofing attacks including image and video attacks.
- KSP Keywords
- Background analysis, Biometric information, Face recognition system, Liveness Detection, Motion information, Spoofing attack, access control, human computer interface