Multi-factor human face living body detection system and method

Abstract

The invention provides a multi-factor human face living body detection system and method, and belongs to the technical field of human face recognition. The system comprises a human face detection module, a human face image preprocessing module, a data storage module, a random number generation module and a multi-factor living body detection module. The method comprises: acquiring face image information and video information, and sending the acquired face image information and video information to a face image preprocessing module and a data storage module; enabling the face image preprocessingmodule to preprocess the received face image information and video information and judge whether the face information meets requirements or not according to a processing result; enabling the random number generation module randomly to generate multi-factor living body detection parameters; and enabling the multi-factor living body detection module to perform multi-factor human face living body detection according to the multi-factor living body detection parameters generated by the random number generation module. According to the method, challenge action combinations are diversified, challenge pools are richer, and the attack difficulty is greatly increased.

Description

technical field [0001] The invention belongs to the technical field of face recognition, and in particular relates to a multi-factor face liveness detection system and method. Background technique [0002] The user identity authentication system is the most important and the first line of defense of the security system. The classic user authentication methods include secret keys, security tokens and biometric features. In most user identity authentication methods, identity authentication based on biometrics has the advantages of convenience, ease of use, and no need for users to memorize, and has become a hot research direction for user identity authentication. All have been paid attention to by many information security researchers in academia and industry. Among them, face authentication is a biometric identification technology based on human facial features for identification. It follows the way humans remember different faces and corresponding identities, and does not r...

AI Technical Summary

Problems solved by technology

Face research is widely used in real life, including China Construction Bank's face login, Alipay's face payment, and face check-in, all of which are based on face research. Well-known domestic and foreign companies such as Google, Microsoft, and Ali , HKUST Xunfei, face++, etc. have successively made higher achievements on human faces. The construction of deeper networks has improved the recognition rate and robustness, but additional high-performance hardware support is required.

The previous face detection system provided more detection methods in face recognition, but compared with the methods based on photo and video attacks, such a system has very low security. Compared with the latest virtual human-based Face attacks, many systems are still difficult to resist similar attacks

Images