Dual-verification face comparison system and method based on Feiteng platform

Abstract

The invention discloses a dual-verification face comparison system and method based on a Feiteng platform. The comparison system comprises an identity information reading module, a field face visiblelight photograph collection module, a living body detection module, a public security high-definition photograph extraction module, a face comparison module and a Feiteng central processor. The comparison method comprises the following steps that: S1: collecting an infrared photograph via the living body detection module; S2: on the basis of the infrared photograph, carrying out living body detection; S3: comparing a visible light photograph with an identity card photograph by the face comparison module; and S4: comparing the visible light photograph with a Ministry of Public Security photograph by the face comparison module. The system has the beneficial effects that face comparison is carried out on the basis of a domestic Feiteng processor framework, and system performance is better; through the living body detection based on the infrared photograph, various types of "face deceiving type" attacks are effectively avoided; and through a technical scheme that a field face photograph isindependently subjected to dual verification with the identity card photograph and the Ministry of Public Security photograph, face identification accuracy is higher.

Description

technical field [0001] This application belongs to the technical field of face recognition, and in particular, relates to a face comparison system and method based on double verification of Feiteng platform. Background technique [0002] As a means of personal identity verification, face recognition technology is more convenient and faster than traditional manual identity verification and new fingerprint recognition verification technology, and is easily accepted by people, so it is widely used in education, finance, railway, etc. Security and other authentication fields, but in the actual application process, the following problems inevitably exist: [0003] (1) Security [0004] For face recognition applications, there is currently a "face spoofing attack" that is difficult to defend against, that is, users pretend to be real people through their own photos, video streams, 3D models, etc. to attack, and compare it with identity information, effectively Deceive the system...

AI Technical Summary

Problems solved by technology

Although the recognition result of this application is not affected by external obstructions such as glasses, eyebrows and hair, and has good stability and high recognition accuracy, it does not take into account the security issues in the field of face recognition applications considered in this patent application

Images