Face identification method and system, terminal and server

A face recognition and server technology, applied in the field of identity authentication, can solve the problem of low security of face recognition and achieve the effect of improving security and practicability

Inactive Publication Date: 2018-01-30
ZTE CORP
View PDF0 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] According to the face recognition method and system, terminal and server provided by the embodiments of the present invention, it mainly solves the technical problem that the existing face recognition technology cannot effectively avoid the low security of face recognition caused by the deception of inanimate prostheses

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 identification method and system, terminal and server
  • Face identification method and system, terminal and server
  • Face identification method and system, terminal and server

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] In order to solve the technical problem that the existing face recognition technology cannot effectively avoid the low security of face recognition caused by inanimate prosthesis deception, the embodiment of the present invention provides a face recognition method, which combines the face recognition process with the living body detection The process is combined, and the face recognition process is completed when the living body detection is passed, so as to effectively identify the current counterfeiting and deception methods and ensure the security and practicability of face recognition authentication.

[0059] In this embodiment, the embodiment of the present invention is described by taking the identification process performed on the terminal side as an example, where the terminals include mobile terminals such as mobile phones and tablet computers, and fixed terminals such as desktop computers. For details, please refer to figure 1 , figure 1 The flow chart of the...

Embodiment 2

[0083] In this embodiment, the embodiment of the present invention is described by taking the recognition process executed on the server side as an example. See figure 2 , figure 2 Another face recognition method flow chart provided in this embodiment, the specific recognition steps are as follows:

[0084] S21. Receive the blood volume pulse wave signal sent by the terminal.

[0085] Specifically, for the concept related to the blood volume pulse wave signal, please refer to the relevant part in the first embodiment, and details will not be repeated here. When the terminal sends the blood volume pulse wave signal to the server, the signal data can be compressed, and then decompressed by the server to obtain the blood volume pulse wave signal, and the server filters the blood volume pulse wave signal to filter out the baseline drift in the signal and high frequency noise.

[0086] S22. Detect whether the face image is a live face image according to the blood volume pulse...

Embodiment 3

[0095] In this embodiment, the embodiment of the present invention is described by taking the recognition process executed on the server side as an example. Compared with the recognition process performed on the server side in Embodiment 2, the face recognition method proposed in this embodiment is mainly aimed at the situation that the terminal image processing capability is limited. Please refer to image 3 , image 3 Another face recognition method flow chart provided in this embodiment, the specific recognition process is as follows:

[0096] S31, receiving at least two face images of at least one heart rate cycle sent by the terminal;

[0097] S32, extracting a blood volume pulse wave signal from the face image;

[0098] S33, detecting whether the face image is a live face image according to the blood volume pulse wave signal;

[0099] S34. If the face image is a live face image, extracting face features from the face image for recognition.

[0100] Compared with the ...

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 embodiment of the invention discloses a face identification method and system, a terminal and a server. At least two face images of a heart rate cycle are collected, and blood volume pulse wave signals are extracted from the at least two face images, and then the blood volume pulse wave signals are sent to a server for living body face detection; when a detection result of the at least two face images are living body face images returned by the server is received, face features are extracted from the at least two face images and sent to the server for face identification to greatly combinea face identification process and a living body detection process, the extracted blood volume pulse wave signals are employed to determined whether a face to be identified is a living body or not, the face identification process is completed in the condition that the face to be identified is the living body, and therefore, the face identification method and system, he terminal and the server havea certain determination ability to effectively improve safety and practicality of face identification.

Description

technical field [0001] The invention relates to the technical field of identity authentication, in particular to a face recognition method and system, a terminal and a server. Background technique [0002] Face recognition technology is an effective identity authentication technology. However, with the widespread use of face recognition technology, various methods have appeared to pretend to be faces to pass identity authentication. The biggest technical challenge that may be faced is the problem of prosthesis deception. In an uncontrollable online environment, criminals will easily forge face videos or make artificial headgear that is no different from real people to pass identity authentication. [0003] At present, various anti-spoofing technologies such as blinking, lip movement or 3D have been developed, but each technology has different problems. For example, speaking can be recorded, and videos with blinking or lip movement can also be generated to deceive the face re...

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 李伟华
Owner ZTE CORP
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