Improving the Security of the Facial Biometrics System Using the Liveness Detection Module

Abstract

Biometric methods are of considerable value when used alone or in combination with other identity verification technologies. Two-dimensional facial recognition approaches provide low cost and convenient recognition system due to convenience and ease of use. Rapid face image substitution is one of the main problems in 2D face area. Biometric systems can be attacked by fakes such as images of people’s faces, masks and videos that are easily accessible from social networks. The typical disadvantage of survivability detection in consumer-grade methods is a significant disadvantage and limits the value of device-built biometric authentication in smartphones and tablets. The work is devoted to the study of methods for verifying the belonging of a biometric sample to a living person. The relevance of the work is due to the expansion of the use of biometric authentication systems and the need to protect the biometric identification and authentication processes from hacking attempts using photographs or video. For the experimental evaluation of the complex application of the studied methods, a prototype of a multi-module system for testing faces using neural networks and heuristic algorithms was developed.