Unlock instant, AI-driven research and patent intelligence for your innovation.

Lip language recognition model training method, living body recognition method and device

A recognition model and lip language technology, applied in the field of living body recognition, can solve problems such as impersonation and easy cracking, and achieve the effect of lowering the threshold and cost, facilitating deployment, and reducing costs

Active Publication Date: 2021-04-13
MASHANG CONSUMER FINANCE CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since these detection techniques are not standardized, they can be easily cracked or impersonated through pre-recorded videos.

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
  • Lip language recognition model training method, living body recognition method and device
  • Lip language recognition model training method, living body recognition method and device
  • Lip language recognition model training method, living body recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The following will clearly and completely describe the technical solutions in the embodiments of the application with reference to the drawings in the embodiments of the application. Apparently, the described embodiments are only some of the embodiments of the application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0036] This application applies lip language recognition technology to living body recognition, and realizes living body recognition through a lip language recognition model based on deep learning.

[0037] Such as figure 1 as shown, figure 1 It is a schematic flowchart of an embodiment of a training method for a lip recognition model based on deep learning in this application. Including the following steps:

[0038] Step 101: Obtain the video data of the user reading the specifi...

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 application discloses a training method for a lip language recognition model, a living body recognition method and a device. The living body recognition method includes: obtaining video data to be detected; preprocessing the video data to obtain a lip region picture corresponding to the video data; Input the lip area picture into the trained lip language recognition model based on deep learning, and output the read content of the video data through the lip language recognition model; wherein, the lip language recognition model includes sequentially cascaded 3D convolutional network structures, 2D convolutional network structure, GRU structure, and CTC loss function; determine whether the video data is video data obtained by a living user reading the specified content according to the edit distance between the read content and the specified content. Through the above method, living body identification can be performed quickly and accurately.

Description

technical field [0001] The present application relates to the technical field of living body recognition, in particular to a training method of a lip recognition model, a living body recognition method and a device. Background technique [0002] With the rapid development of the Internet and biotechnology, identity verification through biometrics has been applied in various industries. Such as mobile payment, access control authentication and so on. In biometric identification, fingerprint identification such as mobile phone unlocking, iris identification, facial feature identification, and more advanced live detection technologies are commonly used. [0003] Liveness detection generally uses combined actions such as blinking, opening the mouth, shaking the head, and nodding, combined with facial key point positioning, face tracking and other technologies to verify whether it is a real living person. However, since these detection techniques are not standardized, they can ...

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): G06K9/00G06K9/62
CPCG06V40/20G06V40/45G06F18/22G06F18/214
Inventor 赵幸福孔志飞赵立军
Owner MASHANG CONSUMER FINANCE CO LTD