Abstract

2D facial identification has attracted a great amount of attention over the past years, due to its several advantages including practicality and simple requirements. However, without its capability to recognize a real user from an impersonator, face identification system becomes ineffective and vulnerable to spoof attacks. With the great evolution of smart portable devices, more advanced sorts of attacks have been developed, especially the replayed videos spoofing attempts that are becoming more difficult to recognize. Consequently, several studies have investigated the types of vulnerabilities a face biometric system might encounter and proposed various successful anti-spoofing algorithms. Unlike spoofing detection for passive or motionless authentication methods that were profoundly studied, anti-spoofing systems applied on interactive user verification methods were broadly examined as a potential robust spoofing prevention approach. This study aims first at comparing the performance of the existing spoofing detection techniques on passive and interactive authentication methods using a more balanced collected dataset and second proposes a fusion scheme that combines both texture analysis with interaction in order to enhance the accuracy of spoofing detection.

Department

Computer Science & Engineering Department

Degree Name

MS in Computer Science

Graduation Date

6-1-2015

Submission Date

December 2015

First Advisor

Moustafa, Mohamed

Committee Member 1

Khalil, Awad

Committee Member 2

Khalil, Mahmoud

Extent

72 p.

Document Type

Master's Thesis

Library of Congress Subject Heading 1

Image alysis.

Library of Congress Subject Heading 2

Biometric identification.

Rights

The author retains all rights with regard to copyright. The author certifies that written permission from the owner(s) of third-party copyrighted matter included in the thesis, dissertation, paper, or record of study has been obtained. The author further certifies that IRB approval has been obtained for this thesis, or that IRB approval is not necessary for this thesis. Insofar as this thesis, dissertation, paper, or record of study is an educational record as defined in the Family Educational Rights and Privacy Act (FERPA) (20 USC 1232g), the author has granted consent to disclosure of it to anyone who requests a copy.

Institutional Review Board (IRB) Approval

Approval has been obtained for this item

Share

COinS