Multi-modal living body detection method and device, computer equipment and storage medium

A technology of computer equipment and living body detection, which is applied in computer components, computing, deception detection, etc., can solve the problem of weak voiceprint algorithm, disjointed face comparison process, poor false recognition rate and false rejection rate of voiceprint recognition algorithm and other issues, to achieve the effect of unifying the authentication process and improving the security of the algorithm

Pending Publication Date: 2021-04-09
BANK OF COMMUNICATIONS
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] 1) The action detection mode is not effective in identifying remake video attacks, and needs to rely on background algorithms for reinforcement identification
[0004] 2) The purpose of motion detection is the follow-up face comparison. Motion detection is based on the client, and the face comparison service is provided by the background. In this mode, the motion detection and face comparison process are disconnected, and there is a certain degree of security Hidden danger
[0005] 3) Action detection needs to use the camera of the mobile phone to take pictures, and there is a possibility that criminals can trick the camera to attack by technical means after invading the mobile phone operating system
Compared with the more mature face recognition technology, the false recognition rate and rejection rate of the voiceprint recognition algorithm are poor
At the same time, the voiceprint algorithm is weak in the live detection function, and is easily affected by various equipment and environments such as audio sampling rate and noise.

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
  • Multi-modal living body detection method and device, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] Such as figure 1 As shown, the present embodiment provides a multimodal living body detection method, which method includes the following steps:

[0037] S1. Obtaining a face image;

[0038] S2. Generate voiceprint verification information and send a voiceprint verification request;

[0039] S3. Collect the voiceprint information to be verified. During the process of collecting the voiceprint information, the face image is continuously obtained. Once the face image is not obtained, return to step S1. After the voiceprint information is collected, step S4 is executed;

[0040] S4. Perform face recognition verification on the images acquired in the above steps, and simultaneously perform voiceprint verification on the acquired voiceprint information;

[0041] S5. Generate a living body detection result according to the face recognition verification and voiceprint verification results.

[0042] The process of acquiring the face image is as follows: acquire the image, de...

Embodiment 2

[0056] This embodiment provides a multimodal living body detection device, which includes:

[0057] Face image acquisition module: This module is used to acquire face images. The process of acquiring face images is as follows: acquire an image, detect whether it is a face through a face detection algorithm, save the face image if it is, otherwise re-acquire the image, obtain The image process is obtained by calling the camera.

[0058] Voiceprint verification request module: This module generates voiceprint verification information and sends a voiceprint verification request. The voiceprint verification information includes a dynamic digital verification code.

[0059]Voiceprint collection module: This module collects the voiceprint information to be verified, and calls the face image acquisition module to continuously acquire face images during the voiceprint collection process to ensure that face images are always collected during the voiceprint collection process.

[0060]...

Embodiment 3

[0065] This embodiment provides a computer device. The computer device includes a processor and a memory, the memory is used to store a computer program, and the processor is used to implement a multimodal living body detection method when the computer program is executed. The multimodal living body detection method in this implementation is the same as that in Embodiment 1, and will not be repeated in this embodiment.

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 relates to a multi-modal living body detection method and device, computer equipment and a storage medium. The multi-modal living body detection method comprises the following steps: S1, acquiring a face image; S2, generating voiceprint verification information, and sending a voiceprint verification request; S3, collecting voiceprint information to be verified, continuously obtaining the face image in the voiceprint information collection process, returning to the step S1 once the face image cannot be obtained, and executing the step S4 after the voiceprint information collection is completed; S4, carrying out face recognition verification on the image obtained in the previous step, and synchronously carrying out voiceprint verification on the obtained voiceprint information; S5, generating a living body detection result according to the face recognition verification result and the voiceprint verification result. Compared with the prior art, the method has the advantages of convenience in detection, high safety and the like.

Description

technical field [0001] The present invention relates to the technical field of biological recognition living body detection devices, in particular to a multi-mode living body detection method, device, computer equipment and storage medium. Background technique [0002] In recent years, face recognition technology has developed rapidly and has been applied to all walks of life. With the application of face recognition technology, corresponding attack methods emerge in endlessly, such as using photos, videos, image synthesis and other technologies to attack face recognition algorithms to deceive algorithms. By embedding the liveness detection function in the face recognition process, such attacks can be effectively prevented. At this stage, the common method of face recognition liveness detection is action detection: the client prompts the action combination of blinking, opening the mouth, nodding, shaking the head, etc., and uses the face recognition algorithm to locate the ...

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): G06K9/00G06F21/32G10L17/00
CPCG06F21/32G10L17/00G06F2221/2133G06V40/161G06V40/172G06V40/70G06V40/45
Inventor 任建新
Owner BANK OF COMMUNICATIONS
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