Face ID Sensor with Aberrated Lens for Anti-Spoofing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Face identification systems are vulnerable to spoofing attacks using photographs or videos, as they cannot effectively distinguish between live faces and fake images, leading to security breaches in electronic access platforms.

Innovation Solution

The implementation of a face ID sensor with an imaging lens comprising a transparent slab and a half-ball lens, which forms modulated images with aberrations, combined with a photodetector to convert optical signals into electrical signals, and a processing module to analyze and compare facial signatures for authentication, utilizing image modulations and retro-reflection to differentiate between live and fake faces.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If conventional face ID sensing is used, then ease of operation is improved, but reliability deteriorates due to vulnerability to spoofing attacks

Engineering Contradiction:
Improveease of operationVSAvoidreliability
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent introduces a structured light pattern as an intermediary between the light source and the face. This pattern modulates the light in a specific way that interacts differently with live facial features versus spoofing materials, enabling the system to distinguish between genuine faces and fake images while maintaining ease of use

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent changes the optical parameters of the imaging system by using a lens with intentional aberrations and a structured light pattern. This modifies the light modulation characteristics so that live faces produce distinct modulation patterns compared to spoofing attempts, thereby improving reliability without compromising ease of operation

Inventive Principle:
Principle #35Parameter changes

2Reliability

If anti-spoofing capabilities are added to face ID sensors, then reliability is improved, but device complexity increases

Engineering Contradiction:
ImprovereliabilityVSAvoiddevice complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent makes the imaging lens serve multiple functions: it acts as both a standard imaging lens and a structured light modulator. The lens with intentional aberrations creates the structured light pattern while still performing normal face imaging, eliminating the need for separate components and reducing overall device complexity

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

Solution Approach 2:

The patent combines the light modulation function and the imaging function into a single integrated lens structure. The structured light pattern is generated through the lens itself rather than requiring a separate modulator, and the same lens captures both the structured light reflection and the facial image, simplifying the device architecture

Inventive Principle:
Principle #5Merging (Combining)

3Measurement precision

If structured light pattern with lens aberrations is used, then measurement precision is improved for distinguishing live faces, but manufacturing precision requirements increase

Engineering Contradiction:
Improvemeasurement precisionVSAvoidmanufacturing precision
Core Design Contradiction:
Measurement precisionVSManufacturing precision

Solution Approach 1:

The patent converts the harmful effect of lens aberrations (which normally degrade image quality) into a beneficial feature. The intentional aberrations create a structured light pattern that enhances the ability to distinguish live faces from spoofing attempts, turning a manufacturing defect into a functional advantage

Inventive Principle:
Principle #22Blessing in disguise (Convert harm into benefit)

Solution Approach 2:

The patent intentionally changes the optical parameters of the lens by introducing controlled aberrations. This deliberate parameter modification creates the structured light modulation pattern needed for anti-spoofing, and the system is designed to work with these specific parameter values rather than requiring perfect optical precision

Inventive Principle:
Principle #35Parameter changes

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 solution enhances the security of electronic access by accurately distinguishing between live and fake faces, preventing unauthorized access and improving the robustness of face identification systems against spoofing attacks.

Implementation Method 1

a photodetector positioned substantially at a focal plane of the imaging lens, and configured to convert optical signals of the modulated image into electrical signals

Methodology Applied
Scientific EffectPhotoelectric Effect: Photoelectric Effect

Implementation Method 2

the combination of the half-ball lens and the transparent slab is configured to form a modulated image having image aberrations of an object

Methodology Applied
Scientific EffectRefraction: Refraction

Implementation Method 3

an imaging lens and a photodetector, and the imaging lens including: a transparent slab and a half-ball lens

Methodology Applied
Scientific EffectLens: Lens

Data Source

PatentEP3721381B1Anti-spoofing face id sensing
Publication Date: 2023.05.10 SHENZHEN GOODIX TECH CO LTD
  • EP3721381B1 patent drawingFigure 1
  • EP3721381B1 patent drawingFigure 2
  • EP3721381B1 patent drawingFigure 3

AI summary

A security check system using face ID sensing for secure access to an electronic platform includes a camera. The camera includes an imaging lens configured to form a modulated image of an object positioned in front of the camera. The modulated image of the object includes deviations from an ideal image. The security check system further includes a computer memory configured to store face ID data of an authorized person. The face ID data is generated from one or more modulated images of a live face of the authorized person acquired by the camera during a registration process. The security check system further includes a processing module configured to analyze the modulated image of the object to extract facial signatures, compare the facial signatures to the face ID data, and determine whether the object is the live face of the authorized person based on the comparison.