Face spoofing detection from single images using active shape models with Stasm and LBP

Face spoofing detection from single images using active shape models with Stasm and LBP

The proposed approach :(a) Viola-Jones algorithm, (b) Active Shape Models with Stasm, (c) Crop and normalzide the face, (d) Feature extraction using LBP and (e) Non-linear SVM classifier for determining a real face or fake.

Authors:

Azeddine Benlamoudi1, Djamel Samai1, Abdelkrim Ouafi2, Abdelmalik Taleb-Ahmed3, Salah Eddine Bekhouche2 Abdenour Hadid4,

  1. Laboratory of LAGE, University of Ouargla, Algeria
  2. Laboratory of LESIA, University of Biskra, Algeria
  3. Laboratory of LAMIH, University of Valenciennes, France
  4. Center for Machine Vision Research, University of Oulu, Finland

Abstract:

Besides the recognition task, todays biometric systems need to cope with additional problem: spoofing attacks, like presenting a photo of a person(client) to camera. We study in this paper an anti-spoofing solution for distinguishing between ‘live’ and ‘fake ‘ faces. In our approach we focused in face detection using Viola-Jones algorithm and Active Shape Models with Stasm for locating landmarks. Then, we apply Local Binary Patterns (LBP) operator to extract the features in each region of the image. Finally, we use a nonlinear Support Vector Machine (SVM) classifier with kernel function for determining whether the input image corresponds to a live face or not. Our experimental analysis on a publicly available database NUAA, showed excellent results compared to existing methods.

Please cite as:

@InProceedings{CVA2015,
Title = {Face spoofing detection from single images using active shape models with Stasm and LBP},
Author = {Benlamoudi, A. and Samai, A. and Ouafi, A. and Taleb-Ahmed, A. and Bekhouche, S. and Hadid, A.},
Booktitle = {Troisième Conférence internationale sur la Vision Artificielle CVA’ 2015},
Year = {2015},
month={Apr},
DOI = {10.13140/RG.2.1.2027.4723}
}

Downloads:

Paper: PDF
Database: NUAA