Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multi-strategy fraud-preventing face recognition method

A face recognition and anti-fraud technology, applied in character and pattern recognition, acquisition/recognition of facial features, instruments, etc., can solve the problems of general resistance and poor user experience, and achieve the effect of preventing identity fraud and low cost

Active Publication Date: 2018-05-08
BEIJING UNIV OF TECH
View PDF5 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional liveness detection methods are often aimed at a single fraudulent method, and forgery attacks are easy to seize the short board to attack
Or use the method of user cooperation for action verification. This method has poor user experience and general resistance

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Multi-strategy fraud-preventing face recognition method
  • Multi-strategy fraud-preventing face recognition method
  • Multi-strategy fraud-preventing face recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] The technical solutions of the present invention will be further specifically described below through examples.

[0014] The invention provides a multi-strategy anti-fraud face recognition method, which is suitable for a near-infrared (NIR) camera video collection platform. According to the idea of ​​"barrel principle", the present invention uses multi-level anti-fraud means in each link of face recognition to improve the security performance of the system. The overall framework is as follows: figure 1 As shown, measures are taken against different fraudulent authentication behaviors, and authentication is performed quickly when the user does not cooperate with the action.

[0015] like figure 1 As shown, the present invention provides a kind of multi-strategy anti-fraud face recognition method, comprising the following steps:

[0016] Step 1: Use the near-infrared camera to collect images for multiple face registration

[0017] Face registration can ensure the authe...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a multi-strategy fraud-preventing face recognition method which comprises the following steps of: 1, in a face detection process, detecting whether bright pupils generated by anear-infrared device exist at eye pupil positions and detecting whether the variance meets a threshold value in a face complexion grayscale section at a face region position, and determining whethera fraudulent behavior attack exists; 2, based on the dynamic property of the face recognition process, in the process of face recognition verification, detecting a micro-expression based on Candide-3model 3D face reconstruction, determining the similarity between the face features in three adjacent frames and the 3D model, and setting a reasonable threshold to avoid an excessively approximate face.

Description

technical field [0001] The invention belongs to the field of biological feature recognition, in particular to a multi-strategy anti-fraud face recognition method. Background technique [0002] At present, face recognition technology is widely used. The main goal of face recognition technology is to identify the identity of face images. However, the face recognition process faces multiple fraudulent means. problems that urgently need to be resolved. Face recognition technology is mainly faced with three fraudulent methods: legitimate user's face picture, legitimate user's face video, and legitimate user's 3D model. Traditional liveness detection methods are often aimed at a single fraudulent method, and forgery attacks are easy to seize the short board to attack. Or use the method of user cooperation to perform action verification. This method has poor user experience and general resistance. Only by using multi-level strategies can we effectively deal with complex and mult...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/00
CPCG06V40/174G06V40/168G06V40/172
Inventor 王素玉于晨
Owner BEIJING UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com