DocumentCode :
3852381
Title :
Face spoofing detection from single images using texture and local shape analysis
Author :
J. Maatta;A. Hadid;M. Pietikainen
Author_Institution :
Center for Machine Vision Research, Department of Computer Science and Engineering, University of Oulu, P.O. Box 4500, FI-90014 Oulu, Finland
Volume :
1
Issue :
1
fYear :
2012
fDate :
3/1/2012 12:00:00 AM
Firstpage :
3
Lastpage :
10
Abstract :
Current face biometric systems are vulnerable to spoofing attacks. A spoofing attack occurs when a person tries to masquerade as someone else by falsifying data and thereby gaining illegitimate access. Inspired by image quality assessment, characterisation of printing artefacts and differences in light reflection, the authors propose to approach the problem of spoofing detection from texture analysis point of view. Indeed, face prints usually contain printing quality defects that can be well detected using texture and local shape features. Hence, the authors present a novel approach based on analysing facial image for detecting whether there is a live person in front of the camera or a face print. The proposed approach analyses the texture and gradient structures of the facial images using a set of low-level feature descriptors, fast linear classification scheme and score level fusion. Compared to many previous works, the authors proposed approach is robust and does not require user-cooperation. In addition, the texture features that are used for spoofing detection can also be used for face recognition. This provides a unique feature space for coupling spoofing detection and face recognition. Extensive experimental analysis on three publicly available databases showed excellent results compared to existing works.
Journal_Title :
IET Biometrics
Publisher :
iet
ISSN :
2047-4938
Type :
jour
DOI :
10.1049/iet-bmt.2011.0009
Filename :
6180283
Link To Document :
بازگشت