Face spoof detection using ensemble classifier

Ajomale, Gbemisola (2021) Face spoof detection using ensemble classifier. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (637kB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

In modern technology, face recognition system has received great attention. Several desktop, web and mobile applications make use of face recognition for security purpose. A major point of concern is the ability of the face recognition system to prevent an authorised person from having access to the application. Face spoofing through pictures and videos often threatens the system module of a face recognition system by disguising as a real image. A detection technique for fase spoofing attack must be such which could be relied on against different mode of attacks. A novel approach to detect spoofed images needs to be developed to reduce and eradicate the effects of spoofing. Several researchers have proposed detection techniques. Some of these past attempts have been reviewed in this paper. I propose in this study, an ensemble machine learning approach for detecting face spoofing. Random forest algorithm an ensemble learning and neural network were used for face spoofing detection. Neural network gave a better classification result.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Random forest; Ensemble learning; Neural networks
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security
Divisions:	School of Computing > Master of Science in Cyber Security
Depositing User:	Clara Chan
Date Deposited:	23 Nov 2022 14:55
Last Modified:	23 Nov 2022 14:55
URI:	https://norma.ncirl.ie/id/eprint/5924

Actions (login required)

View Item