Anti-fraud method and system based on LipNet algorithm, and electronic equipment

An algorithm and algorithm model technology, applied in computing, computer parts, electrical and digital data processing, etc., can solve problems such as breakthroughs in robot preventive measures and increase the difficulty of cracking.

Pending Publication Date: 2021-08-27
SHANGHAI QIYUE INFORMATION TECH CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Face recognition technology is also constantly improving. From the initial recognition of static images, it is possible to add supplementary actions such as blinking, opening mouth, and turning head to increase the difficulty of cracking. However, there are some new technical means to blink and open static images. The realistic imitation of such actions makes it possible to break through the preventive measures against robots in the face recognition stage of anti-fraud

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
  • Anti-fraud method and system based on LipNet algorithm, and electronic equipment
  • Anti-fraud method and system based on LipNet algorithm, and electronic equipment
  • Anti-fraud method and system based on LipNet algorithm, and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0075] This embodiment is mainly based on the efficient lipNet algorithm, adds voice information to the liveness detection, performs lip language recognition, improves the attacker's technical threshold, and strengthens the risk prevention of counterfeiting.

[0076] Such as figure 1 As shown, the main technical solutions of this embodiment include:

[0077] The collection and processing of the first corpus

[0078] Considering the age and geographical differences of credit users, part of the collection of corpus comes from news media such as news broadcasts and morning news, and part of it comes from Mandarin videos with regional characteristics. The screening of corpus focuses on different age groups, different genders and the repetition of sentences, so as to evaluate the effect of the model.

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 an anti-fraud method and system based on a LipNet algorithm and electronic equipment, and the method comprises the steps: randomly selecting one or more sentences from delineated N sentences for a user to read for an occasion where identity confirmation needs to be carried out, collecting user video data, and inputting the user video data into a LipNet algorithm model for prediction; if the prediction result is lower than a classification threshold value, judging that the user is a robot, wherein N is a natural number. According to the method, the LipNet algorithm is adopted, the current simulation level cannot simulate the corresponding lip language according to the voice, the lip language is applied to an anti-fraud face recognition stage, sentences randomly selected in a delineated range are added, and a user cannot perform machine simulation action in advance, so that a high-risk behavior that someone performs counterfeit by utilizing a high and new technology means can be prevented, and the safety degree of the face recognition technology is improved.

Description

technical field [0001] The invention belongs to the technical field of image speech recognition, especially the field of machine learning-assisted image speech recognition technology, and more specifically relates to an anti-fraud method and system based on LipNet algorithm, electronic equipment and computer storage medium. Background technique [0002] With the development of image technology, the application range of face recognition technology is becoming wider and wider, such as identity recognition, face payment, on-site monitoring, etc. Face recognition technology is also constantly improving. From the initial recognition of static images, it is possible to add supplementary actions such as blinking, opening mouth, and turning head to increase the difficulty of cracking. However, there are some new technical means to blink and open static images. The realistic imitation of such actions makes it possible to break through the preventive measures against robots in the fac...

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): G06N3/04G06K9/62G06K9/00G06F40/216G10L17/18
CPCG06F40/216G10L17/18G06V40/16G06V20/46G06N3/044G06N3/045G06F18/214
Inventor 陈雪清孙涛
Owner SHANGHAI QIYUE INFORMATION TECH CO LTD
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