Biometric Authentication Liveness Detection via Dynamic Pupil Response

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Biometric authentication systems in small handheld devices can be spoofed using recorded data, as they typically rely on static measurements that can be easily replicated, posing a security risk due to the device's sensitive nature and increasing capabilities.

Innovation Solution

Implementing a method that captures biometric measurements before and after a change in a bodily feature, such as pupil size or facial expression, to differentiate between live inputs and recorded data, using techniques like red-eye analysis and multiple image capture to verify the authenticity of the user.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If static biometric measurements are used for authentication, then the authentication process is simple and fast, but the system becomes vulnerable to spoofing with recorded data

Engineering Contradiction:
Improveauthentication process simplicityVSAvoidsecurity against spoofing
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent transforms static biometric authentication into a dynamic process by capturing images before and after a physiological change (such as pupil contraction in response to light). This dynamic measurement ensures the subject is alive and present, preventing spoofing with static recorded data while maintaining user-friendly operation

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system performs preliminary actions by first capturing a baseline biometric image, then inducing a controlled physiological change, and finally capturing a second image to compare. This preliminary sequence of actions creates a reliable authentication process that remains simple for the user to execute

Inventive Principle:
Principle #10Preliminary action

2Reliability

If multiple images are captured to verify liveness, then security against spoofing is improved, but the authentication process becomes more complex

Engineering Contradiction:
Improvesecurity against spoofingVSAvoidauthentication process complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent merges the liveness detection function with the existing biometric authentication process by using the same imaging infrastructure. Multiple images are captured as part of the normal authentication flow, combining security verification with the primary authentication function without requiring separate complex systems

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The system changes the temporal parameter of image capture by taking multiple images at different times (before and after physiological change). This parameter change approach simplifies the overall system design compared to complex spatial or spectral analysis methods, as it uses the same sensor and processing pipeline

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

Enhances security by making it difficult to spoof the system with recorded data, ensuring that only live biometric inputs are accepted, thereby protecting sensitive information and financial resources.

Implementation Method 1

An illuminator may then be activated to cause the pupil of the user's eye to contract

Methodology Applied
Scientific EffectLight: Light

Data Source

PatentEP3588345B1Controlled access to functionality of a wireless device
Publication Date: 2024.11.27 INTEL CORP
  • EP3588345B1 patent drawingFigure 1
  • EP3588345B1 patent drawingFigure 2
  • EP3588345B1 patent drawingFigure 3

AI summary

Various embodiments of the invention may be used to verify that a person being authorized by biometric techniques to use a device is a living person and not some form of recording intended to spoof the system. Some embodiments may try to cause a change in a measured biometric feature, and compare images taken before and after the change to verify the change occurred. In some embodiments, multiple stages of verification may be used, either to increase the difficulty of spoofing the security system, or to provide different levels of security for different levels of access to the device's functionality.