Face liveness detection using defocus

Sooyeon Kim, Yuseok Ban, Sang Youn Lee

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

In order to develop security systems for identity authentication, face recognition (FR) technology has been applied. One of the main problems of applying FR technology is that the systems are especially vulnerable to attacks with spoofing faces (e.g., 2D pictures). To defend from these attacks and to enhance the reliability of FR systems, many anti-spoofing approaches have been recently developed. In this paper, we propose a method for face liveness detection using the effect of defocus. From two images sequentially taken at different focuses, three features, focus, power histogram and gradient location and orientation histogram (GLOH), are extracted. Afterwards, we detect forged faces through the feature-level fusion approach. For reliable performance verification, we develop two databases with a handheld digital camera and a webcam. The proposed method achieves a 3.29% half total error rate (HTER) at a given depth of field (DoF) and can be extended to camera-equipped devices, like smartphones.

Original languageEnglish
Pages (from-to)1537-1563
Number of pages27
JournalSensors (Switzerland)
Volume15
Issue number1
DOIs
Publication statusPublished - 2015 Jan 14

Fingerprint

Face recognition
histograms
attack
Technology
digital cameras
Smartphones
Digital cameras
fusion
cameras
Security systems
Databases
Authentication
Equipment and Supplies
gradients
Fusion reactions
Cameras
Facial Recognition

All Science Journal Classification (ASJC) codes

  • Analytical Chemistry
  • Atomic and Molecular Physics, and Optics
  • Biochemistry
  • Instrumentation
  • Electrical and Electronic Engineering

Cite this

Kim, Sooyeon ; Ban, Yuseok ; Lee, Sang Youn. / Face liveness detection using defocus. In: Sensors (Switzerland). 2015 ; Vol. 15, No. 1. pp. 1537-1563.
@article{2ed82b7cf08f44f2b3ef0f34d46e3b52,
title = "Face liveness detection using defocus",
abstract = "In order to develop security systems for identity authentication, face recognition (FR) technology has been applied. One of the main problems of applying FR technology is that the systems are especially vulnerable to attacks with spoofing faces (e.g., 2D pictures). To defend from these attacks and to enhance the reliability of FR systems, many anti-spoofing approaches have been recently developed. In this paper, we propose a method for face liveness detection using the effect of defocus. From two images sequentially taken at different focuses, three features, focus, power histogram and gradient location and orientation histogram (GLOH), are extracted. Afterwards, we detect forged faces through the feature-level fusion approach. For reliable performance verification, we develop two databases with a handheld digital camera and a webcam. The proposed method achieves a 3.29{\%} half total error rate (HTER) at a given depth of field (DoF) and can be extended to camera-equipped devices, like smartphones.",
author = "Sooyeon Kim and Yuseok Ban and Lee, {Sang Youn}",
year = "2015",
month = "1",
day = "14",
doi = "10.3390/s150101537",
language = "English",
volume = "15",
pages = "1537--1563",
journal = "Sensors",
issn = "1424-3210",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "1",

}

Face liveness detection using defocus. / Kim, Sooyeon; Ban, Yuseok; Lee, Sang Youn.

In: Sensors (Switzerland), Vol. 15, No. 1, 14.01.2015, p. 1537-1563.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Face liveness detection using defocus

AU - Kim, Sooyeon

AU - Ban, Yuseok

AU - Lee, Sang Youn

PY - 2015/1/14

Y1 - 2015/1/14

N2 - In order to develop security systems for identity authentication, face recognition (FR) technology has been applied. One of the main problems of applying FR technology is that the systems are especially vulnerable to attacks with spoofing faces (e.g., 2D pictures). To defend from these attacks and to enhance the reliability of FR systems, many anti-spoofing approaches have been recently developed. In this paper, we propose a method for face liveness detection using the effect of defocus. From two images sequentially taken at different focuses, three features, focus, power histogram and gradient location and orientation histogram (GLOH), are extracted. Afterwards, we detect forged faces through the feature-level fusion approach. For reliable performance verification, we develop two databases with a handheld digital camera and a webcam. The proposed method achieves a 3.29% half total error rate (HTER) at a given depth of field (DoF) and can be extended to camera-equipped devices, like smartphones.

AB - In order to develop security systems for identity authentication, face recognition (FR) technology has been applied. One of the main problems of applying FR technology is that the systems are especially vulnerable to attacks with spoofing faces (e.g., 2D pictures). To defend from these attacks and to enhance the reliability of FR systems, many anti-spoofing approaches have been recently developed. In this paper, we propose a method for face liveness detection using the effect of defocus. From two images sequentially taken at different focuses, three features, focus, power histogram and gradient location and orientation histogram (GLOH), are extracted. Afterwards, we detect forged faces through the feature-level fusion approach. For reliable performance verification, we develop two databases with a handheld digital camera and a webcam. The proposed method achieves a 3.29% half total error rate (HTER) at a given depth of field (DoF) and can be extended to camera-equipped devices, like smartphones.

UR - http://www.scopus.com/inward/record.url?scp=84921285122&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84921285122&partnerID=8YFLogxK

U2 - 10.3390/s150101537

DO - 10.3390/s150101537

M3 - Article

AN - SCOPUS:84921285122

VL - 15

SP - 1537

EP - 1563

JO - Sensors

JF - Sensors

SN - 1424-3210

IS - 1

ER -