Living body verification method and system

A verification method, living body technology, applied in the field of face recognition, can solve problems such as difficult to be recognized

Pending Publication Date: 2018-07-10
北京万相融通科技股份有限公司
View PDF8 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to solve the technical defect that it is difficult to be identified when using the photo of the counterfeit person to carry out malicious attacks based on the face of the identity verification system in the prior art, and the technical defect that the verified person needs to actively cooperate when identifying such malicious attacks, the present invention provides A living body verification method and its system, the purpose of which is to be identified no matter when a counterfeiter uses a photo, a 3D mask, etc. Verification time, improve verification accuracy

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
  • Living body verification method and system
  • Living body verification method and system
  • Living body verification method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] Embodiment 1: A kind of in vivo verification method, refer to figure 1 shown, including the following steps:

[0068] (1) Detect the human face in the visible spectrum imaging picture, and obtain the position data of the detected human face image; for example, the coordinate data of the human face image in the entire shooting picture,

[0069] (2) according to the face image position data obtained in step (1), calculate the position data of described face image in the infrared spectrum imaging picture;

[0070] (3) According to the position data of the described human face image obtained in step (2) in the infrared spectrum imaging picture, detect the human face within the range of the position data of the infrared spectrum imaging picture, and calculate the described human face after detecting the human face Image GLCM feature parameters, the calculated face image GLCM feature parameters are input to the SVM vector machine for comparison, and it can be judged whether ...

Embodiment 2

[0118] Embodiment 2: In addition to the disclosed content of Embodiment 1, in order to further make the detection method of the present invention faster, refer to image 3 As shown, in the step (1), after the human face is detected in the visible spectrum imaging screen, it is first compared with the pre-stored photos and / or the read photos, and if the comparison results are inconsistent, it will end directly.

[0119] It is also possible to detect a human face within the range of the position data of the infrared spectrum imaging picture in the step (3), if no human face is detected, the process ends directly.

[0120] After the above steps, you can directly output wrong results without entering the subsequent comparison process, saving comparison time.

[0121] The system also includes a microprocessor, the microprocessor is respectively connected with the visible spectrum imaging module, the module for obtaining the position data of the visible spectrum image, the module fo...

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 living body verification method, which comprises the following steps that: (1) in a visible spectrum imaging picture, obtaining position data where a face image is positioned; (2) calculating the position data of the face image in an infrared spectral imaging picture; (3) calculating a face image GLCM (Ground Launched Cruise Missile) feature parameter, and adopting a SVM(Support Vector Machine) to judge whether a face is a real face or not. The invention also discloses a living body verification system, which comprises a visible spectral imaging module, a module forobtaining visible spectral image position data, a switching position data module, an infrared structure light projection module, an infrared spectral imaging module, a GLCM feature parameter module and a SVM. The method and the system have the advantages that a copycat can identity hostile attacks when the copycat uses pictures, 3D masks and the like to carry out the hostile attacks on a face-based identity verification system, in addition, a verified person does not need to actively cooperate, so that verification time is shortened, and verification accuracy is improved.

Description

technical field [0001] The invention belongs to the technical field of face recognition, in particular to a living body verification method and system thereof. Background technique [0002] At present, face-based identity verification systems have been widely used. In face-based identity verification systems, identity verification is performed based on the comparison between the currently captured face photo and the pre-stored face photo. With the promotion of face-based authentication systems, some methods of maliciously attacking face authentication have been derived. For example, counterfeiters use the photos or pre-recorded videos of the counterfeit person stored in the handheld terminal to counterfeit themselves for identity verification. However, this counterfeiting method can be easily identified in the prior art, but when the photo of the counterfeited person is placed in front of the camera in this identity verification system based on face photo comparison, this me...

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
CPCG06V40/161G06V40/172G06V40/45
Inventor 闫少建李霈马玉田周聪石锦侃王建军张秋利杜秋超赵金龙
Owner 北京万相融通科技股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap