Face Spoofing Detection From Single Images Using Active Shape Models with Stasm And LBP

Azeddine Benlamoudi , Djamel Samai , Abdelkrim Ouafi , Abdelmalik Taleb-Ahmed (1) , Salah Eddine Bekhouche , Abdenour Hadid (2)

1 LAMIH - Laboratoire d'Automatique, de Mécanique et d'Informatique industrielles et Humaines - UMR 8201
2 CMV - Center for Machine Vision Research

Besides the recognition task, todays biometric sys-tems need to cope with additional problem: spoofing attacks, likepresenting a photo of a person(client) to camera. We study inthis paper an anti-spoofing solution for distinguishing between’live’ and ’fake ’ faces. In our approach we focused in facedetection using Viola-Jones algorithm and Active Shape Modelswith Stasm for locating landmarks. Then, we apply Local BinaryPatterns (LBP) operator to extract the features in each region ofthe image. Finally, we use a nonlinear Support Vector Machine(SVM) classifier with kernel function for determining whether theinput image corresponds to a live face or not. Our experimentalanalysis on a publicly available database NUAA, showed excellentresults compared to existing methods

Mots clés: "BIOMETRIC"; "SPOOFING"; "STASM"; "LBP"; "SVM"; "NUAA"

Domaines: Automatique / Robotique

Azeddine Benlamoudi, Djamel Samai, Abdelkrim Ouafi, Abdelmalik Taleb-Ahmed, Salah Eddine Bekhouche, et al.. Face Spoofing Detection From Single Images Using Active Shape Models with Stasm And LBP. CVA’ 2015, Apr 2015, Tizi Ouzou, Algeria. ⟨hal-03417226⟩