Institutions | About Us | Help | Gaeilge
rian logo


Mark
Go Back
Authentication based on face recognition under uncontrolled conditions
Tavakolian, Niloofar; Nazemi, Azadeh; Azimifar, Zohreh
This paper describes a method to address is- sues regarding uncontrolled conditions in face recognition. This method using mask projection, extracts affecting factor from the test sample and adds it to all normal training samples then compares test sample with all synthetic affected training samples. The method has been applied for multi-factor authentication/verification based on face biometric. Obtained results indicate high accuracy in the lake of sufficient training samples for each class(single sample classes). of the claimed user.
Keyword(s): occlusion; face authentication; face identification; face verification; mask projection; Training Testing; Face recognition; Feature extraction; , Face; Image color analysis
Publication Date:
2017
Type: Other
Peer-Reviewed: Unknown
Language(s): English
Institution: Dublin City University
Citation(s): Tavakolian, Niloofar, Nazemi, Azadeh ORCID: 0000-0002-1138-309X <https://orcid.org/0000-0002-1138-309X> and Azimifar, Zohreh (2017) Authentication based on face recognition under uncontrolled conditions. In: 2017 Artificial Intelligence and Signal Processing Conference (AISP), 25-27 Oct 2017, Shiraz, Iran.
Publisher(s): IEEE
File Format(s): application/pdf
Related Link(s): http://doras.dcu.ie/23042/1/IEEE_Conference%20edition%206.pdf,
https://doi.org/10.1109/AISP.2017.8324120
First Indexed: 2019-02-28 06:08:10 Last Updated: 2020-09-04 06:14:37