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

Live body verification method and device

A verification method, living body technology, applied in the field of biometrics, can solve problems such as incorrect living body verification results, and achieve the effect of eliminating the impact

Active Publication Date: 2020-12-29
BEIJING SENSETIME TECH DEV CO LTD
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Therefore, the technical problem to be solved by the present invention is to overcome the problem in the related art that in the process of biometric verification by checking the blinking movement, it is impossible to rule out the fake blinking movement that forms a local movement of the eye to simulate blinking, which leads to incorrect biometric verification results. phenomenon, thereby providing a living body verification method and device

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
  • Live body verification method and device
  • Live body verification method and device
  • Live body verification method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] In this embodiment, a living body verification method is provided, figure 1 It is a flowchart of the living body verification method in Embodiment 1 of the present invention, such as figure 1 As shown, the process includes the following steps:

[0047] Step S11: Obtain the face video to be verified.

[0048] Step S12: Extract multiple frames of human face and eye images in the human face video to be verified.

[0049] Step S13: Judgment of eye opening and closing is performed on multiple frames of human face and eye images to obtain a first feature value of eye opening and closing.

[0050] Step S14: Judgment of occluded eyes is performed on multiple frames of human face and eye images to obtain the first feature value of occluded eyes.

[0051] Step S15: Verifying whether the face corresponding to the face video to be verified is a live human face according to at least the first feature value of open and closed eyes and the first feature value of occluded eyes.

[...

Embodiment approach

[0075] As a preferred implementation manner, step S45 specifically includes the following sub-steps:

[0076] Step S45.1: Using the method of face tracking and face key feature point alignment, obtain the coordinate information of the face key feature points of the two frames of face images in the video.

[0077] Step S45.2: According to the coordinate information of the key feature points of the two frames of face images in step S45.1, calculate the relative movement of the face in the two frames of face images.

[0078] The above steps involve calculating the motion velocity value of the face image in the face video to be verified. It should be noted that there are various methods for calculating the motion velocity value of the face image, which will be illustrated below with an example. In an optional embodiment, obtain the coordinate information of the key feature points of the human face of two adjacent frames of human face images in the human face video to be verified, ...

Embodiment 2

[0093] This embodiment provides a living body verification device, such as Image 6 Shown, comprise: acquisition module 62, be used to obtain the human face video to be verified; Extraction module 64, be used to extract the multi-frame human face eye image in this human face video to be verified; The first feature value acquisition module 66 , for judging whether to open or close eyes to the multiple frames of human face and eye images, to obtain the first feature value of opening and closing eyes; the second eigenvalue acquisition module 68 is used to determine whether to block eyes to multiple frames of human face and eye images, Obtain the first occluded eye feature value; the verification module 70 is used to at least verify whether the face corresponding to the face video to be verified is a live human face according to at least the first open-closed eye eigenvalue and the first occluded eye feature value.

[0094] The above-mentioned device solves the problem in the rela...

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 present invention provides a method and device for living body verification, wherein the method comprises: obtaining a face video to be verified; extracting multiple frames of face and eye images in the face video to be verified; The eye image is judged to open and close the eyes, and the first feature value of the open and closed eyes is obtained; the occlusion eye judgment is performed on the multi-frame face and eye images, and the first feature value of the occluded eye is obtained; An occluded eye feature value verifies whether the face corresponding to the face video to be verified is a real human face. The invention solves the problem that in the related art, in the process of verifying the living body by checking the eye blinking movement, it is impossible to exclude the fake blinking movement that forms a local movement in the eye to simulate the blinking, resulting in an incorrect result of the living verification, thereby eliminating the situation of fake blinking Influence on in vivo verification results.

Description

technical field [0001] The invention relates to the field of biological identification, in particular to a living body verification method and device. Background technique [0002] Face recognition technology has matured. However, in most applications, in addition to face recognition, face verification is also required to prevent illegal users from cheating through paper photos or electronic screen photos. [0003] Many of the existing in vivo verification methods are based on detecting eye blinking movements for in vivo verification. However, these methods often only design how to detect the movement of blinking (for example: CN101216887A, CN103400122A), but do not consider how to resist the deceptive way of simulating blinking by causing local movements in the eyes. In addition, the living body verification method based on optical flow (for example: CN101908140A), by detecting the change of optical flow in the live face image, judges whether the face to be tested is a li...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/08
CPCG06N3/084G06V40/166G06V40/45G06F18/24
Inventor 吴立威彭义刚罗梓鑫曹旭东李诚
Owner BEIJING SENSETIME TECH DEV CO LTD
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