Face Recognition Lip Movement Voice Synchronization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional human face recognition systems are vulnerable to image counterfeiting attacks, where a real photo is used to impersonate a person, leading to low security and difficulty in distinguishing between real individuals and images.

Innovation Solution

A human face recognition method and system that dynamically verifies the authenticity of individuals by generating a statement and matching lip movement and voice information against a preset rule, preventing attacks using real photos by ensuring synchronization between audio and video data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional human face recognition systems use only visual feature information for identity authentication, then the recognition process is simple and fast, but the system becomes vulnerable to image counterfeiting attacks and has low security

Engineering Contradiction:
ImprovesecurityVSAvoidrecognition process complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent combines multiple biometric verification methods (face recognition, voice recognition, lip movement recognition) into a unified authentication system. The system simultaneously processes visual feature information, audio data, and video data to perform comprehensive identity verification, making it difficult for attackers to bypass all verification layers with a single type of counterfeit attack

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The system dynamically switches between different verification modes and adjusts the verification process based on real-time analysis. It performs dynamic lip movement analysis by comparing actual lip movements with expected movements derived from voice information, creating a dynamic verification process that adapts to different authentication scenarios and threats

Inventive Principle:
Principle #15Dynamics

2Reliability

If the system performs only static face recognition, then the authentication is quick, but it cannot distinguish between real individuals and photos

Engineering Contradiction:
Improveauthenticity verificationVSAvoidauthentication time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary face recognition to quickly identify the user, then immediately follows up with dynamic verification of lip movements and voice characteristics. This preliminary action allows the system to quickly filter out obvious counterfeit attempts while maintaining thorough verification for legitimate users

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system continuously monitors and analyzes lip movements in real-time during the authentication process, maintaining continuous verification of the user's authenticity throughout the interaction rather than performing a single static check, ensuring that the verification process remains ongoing and adaptive

Inventive Principle:
Principle #20Continuity of useful action

Data Source

PatentUS10650259B2Human face recognition method and recognition system based on lip movement information and voice information
Publication Date: 2020.05.12 TENCENT TECHNOLOGY (SHENZHEN) CO LTD
  • US10650259B2 patent drawing
  • US10650259B2 patent drawing
  • US10650259B2 patent drawing

AI summary

The embodiment of the present invention provides a human face recognition method and recognition system. The method includes that: a human face recognition request is acquired, and a statement is randomly generated according to the human face recognition request; audio data and video data returned by a user in response to the statement are acquired; corresponding voice information is acquired according to the audio data; corresponding lip movement information is acquired according to the video data; and when the lip movement information and the voice information satisfy a preset rule, the human face recognition request is permitted. By performing fit goodness matching between the lip movement information and voice information in a video for dynamic human face recognition, an attack by human face recognition with a real photo may be effectively avoided, and higher security is achieved.