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

Face live detection method

A technology of living body detection and camera, applied in the direction of instruments, character and pattern recognition, computer parts, etc., can solve problems such as low efficiency, and achieve the effect of simple method

Inactive Publication Date: 2018-01-19
深圳元见智能科技有限公司
View PDF5 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the shortcomings of low efficiency in the living body detection method of human face recognition in the visible light mode, the present invention provides a human face living body detection method under visible light, and the method includes the steps of:

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
  • Face live detection method
  • Face live detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] In order to make the technical means realized by the present invention clear, the present invention will be further described below in conjunction with the accompanying drawings.

[0018] like figure 1 As shown, first set up the front camera and the side camera, the two cameras are in a horizontal position, the front camera directly captures the frontal image of the face, and the side camera is for auxiliary shooting, and the angle between the front camera and the side camera is 15-20 degrees. between; the angle intersection formed is the most suitable area for shooting.

[0019] When the face enters 40-60 cm in front of the front camera, the front camera and the side camera simultaneously capture the face and form a pair of information; the two cameras take more than two groups of photos at the same time, and select a group of clear ones for follow-up Steps, if not clear, shoot again. The method of using feature points to determine whether a person is directly in fro...

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 provides a face live detection method comprising the steps that S1. the photographing frame inclined angle formed by a front camera and a side camera is set to be between 15-20 degrees;S2. the front camera and the side camera simultaneously snapshoot the face and form group pair information; S3. quality analysis is performed on the photo snapshot by the front camera; S4. comparisonwith a face feature library is performed to determine the identity of the face, and then comparison is performed by using the snapshot group pair information image; and S5. after the identity of the face is determined, the snapshot group pair information camera face angle is judged by using the feature points, the face is live if the angle difference value of the front camera and the side camera is within the range of 15-20 degrees, and the face is the photo if the angle difference value is within the range of 0-5 degrees. Double cameras forming the inclined angle are adopted to perform simultaneous snapshooting for group pair detection and group pair comparison so that the method is simple, and the defect of low efficiency of the face recognition live detection method through the visiblelight mode can be solved.

Description

[technical field] [0001] The invention relates to the field of biological feature recognition, in particular to a human face liveness detection method under visible light. [Background technique] [0002] With the development of biometric technology, face recognition technology has become mature. At present, under good lighting conditions and postures, the face recognition system can already perform relatively accurate face detection and recognition. However, for some For the face recognition system of access control, login and other systems, users can deceive the system by using illegal means such as photos to pretend to be legitimate users. When performing identity authentication, a photo, recorded video or wax figure of a legitimate user may be placed In this case, the face image collected by the authentication server may successfully match the face image registered by the legitimate user, so the authentication server determines that the attacker is the legitimate user. F...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00
Inventor 廖俊辉刘立军胡楚周
Owner 深圳元见智能科技有限公司
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