Facial Recognition Depth Verification Anti-Counterfeiting

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Facial recognition technologies in electronic devices have low security due to reliance on two-dimensional image verification, which can be compromised by photos, leading to potential information leakage and property loss.

Innovation Solution

The implementation of a facial recognition method using an electronic device equipped with an infrared projector and dual-pass cameras that collect both two-dimensional and depth information, performing triple recognition through two-dimensional image authentication, depth anti-counterfeiting, and infrared anti-counterfeiting to verify the authenticity of a face.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If two-dimensional image verification is used for facial recognition, then the operation is simple and fast, but the security is low and vulnerable to photo attacks

Engineering Contradiction:
Improvefacial recognition operationVSAvoidsecurity
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent transitions from two-dimensional image verification to three-dimensional depth verification by introducing depth information acquisition through stereoscopic vision. The system captures depth maps and calculates depth values for facial features, creating a third dimension of verification that photos cannot replicate, thus resolving the security vulnerability while maintaining operational simplicity

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The patent introduces an intermediary depth verification layer between the user and the authentication system. Instead of directly verifying two-dimensional images, the system first verifies depth information as an intermediary step, which acts as a mediator to block photo attacks while allowing genuine facial recognition to proceed

Inventive Principle:
Principle #24Intermediary (Mediator)

2Device complexity

If only two-dimensional image authentication is performed, then the device complexity is low, but the security performance is insufficient

Engineering Contradiction:
Improvefacial recognition systemVSAvoidsecurity performance
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The patent makes the existing camera system multi-functional by enabling it to capture both two-dimensional images and depth information simultaneously. The same camera hardware performs dual functions: traditional 2D facial recognition and new 3D depth verification, eliminating the need for separate dedicated depth sensors and maintaining device complexity at acceptable levels

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent changes the verification parameter from purely two-dimensional image data to include three-dimensional depth data. By calculating depth values for facial features and comparing them against stored depth information, the system enhances security performance through parameter expansion rather than hardware proliferation

Inventive Principle:
Principle #35Parameter changes

3Reliability

If depth information verification is added to facial recognition, then the security is improved, but the device complexity increases

Engineering Contradiction:
ImprovesecurityVSAvoidfacial recognition system
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent merges depth information acquisition and processing into the existing facial recognition workflow. The depth map calculation and feature point depth verification are integrated with the traditional two-dimensional image authentication process, combining multiple verification functions into a unified system that improves security without proportionally increasing complexity

Inventive Principle:
Principle #5Merging (Combining)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach significantly enhances security by accurately distinguishing between real faces and photos, preventing unauthorized access and information leakage, thereby improving the overall security performance of the electronic device.

Implementation Method 1

emits infrared light with a light spot by using the infrared projector

Methodology Applied
Scientific EffectInfrared radiation: Infrared Radiation

Implementation Method 2

collects first image information of the first object by using the first camera, and collects second image information of the first object by using the second camera

Methodology Applied
Scientific EffectOptical imaging: Lens

Implementation Method 3

calculates depth information of the first object based on the first image information, the second image information, the first length, a lens focal length of the first camera, and a lens focal length of the second camera

Methodology Applied
Scientific EffectParallax: Parallax

Data Source

PatentUS12154373B2Facial recognition method and electronic device
Publication Date: 2024.11.26 HONOR DEVICE CO LTD
  • US12154373B2 patent drawing
  • US12154373B2 patent drawing
  • US12154373B2 patent drawing

AI summary

A facial recognition method includes receiving, by an electronic device, a first instruction triggering the electronic device to perform facial recognition, emitting in response to the first instruction, infrared light with a light spot using an infrared projector, collecting first image information of a first object using a first camera, collecting second image information of the first object using a second camera, calculating depth information of the first object based on the first image information, the second image information, the first length, a lens focal length of the first camera, and a lens focal length of the second camera, and performing user identity verification on the first object using the first image information and the depth information of the first object.