Fast Identity Online-Based Facial Authentication System Development in Mobile

Abstract

Recently, research on methods to improve upon the security vulnerability of password based authentication is being actively conducted. Research on how to use real-time biometric recognition is also actively underway. The system development of Public Key Infrastructure (PKI) key pairs and uses a method that safely stores the produced keys in secure zones, and encryption key data is composed so that access can only be made in Fast Identity Online (FIDO) Authenticator zones. Face certification data extracted from the face recognition engine is created, data can be accessed and saved through encryption. With the Fast Identity Online (FIDO) Authenticator, a method was developed that compares and face certification data. The system in this thesis developed a Fast Identity Online (FIDO) based face certification system that uses biometric authentication to supplement the weaknesses of password based systems which were used for user certification in the past because they cost little and are convenient. System development in this thesis was conducted by applying a Fast Identity Online (FIDO) based certification system to an Active Shape Model (ASM) style face recognition algorithm. After taking a photo of the face with the user’s cellular phone and saving it, certification is carried out through comparisons made of the photo and real-time input images. Once certification is made using Fast Identity Online (FIDO) protocols, tests of face detection speed and matching speed are conducted to measure accuracy and speed. A total of 30 tests were conducted and test results showed that detection speed was an average of 30.35 f/s and matching speed was 14.16 ms. In this paper, biometric authentication security and convenience are provided by using security functions provided by user devices and supplementing them with a server operation method.