Facial Recognition Liveness Detection via Movement Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current facial recognition technologies are vulnerable to impersonation by two- or three-dimensional masks and require specialized hardware to differentiate between live and static facial representations, lacking robust liveness verification.

Innovation Solution

A system that uses an image capture device to scan facial features, authenticates them against a stored facial depth map, and requires users to perform specific movements to verify liveness, utilizing a machine-learning model to recognize and classify landmark points and detect animated facial features, thereby preventing unauthorized access.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If facial recognition is implemented without liveness detection, then authentication speed is improved, but security deteriorates due to vulnerability to mask impersonation

Engineering Contradiction:
Improveauthentication speedVSAvoidsecurity
Core Design Contradiction:
SpeedVSReliability

Solution Approach 1:

The system performs preliminary liveness detection by analyzing facial movements and characteristics before final authentication is granted. This preliminary check ensures the subject is a live person rather than a mask or photograph, preventing impersonation attacks while maintaining fast authentication for legitimate users.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system provides feedback by analyzing various facial characteristics (eye movement, facial muscle movements, depth information) and using this feedback to determine liveness. This feedback mechanism enables the system to distinguish between live faces and masks without significantly increasing authentication time.

Inventive Principle:
Principle #23Feedback

2Measurement precision

If specialized hardware like depth-detecting cameras is used, then liveness detection accuracy is improved, but device complexity increases

Engineering Contradiction:
Improveliveness detection accuracyVSAvoidhardware requirements
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system achieves liveness detection using a standard camera that can perform multiple functions: capturing facial images for recognition and analyzing facial movements for liveness detection. This eliminates the need for specialized depth-detecting cameras while maintaining accurate liveness verification through software-based analysis of facial characteristics.

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

Solution Approach 2:

The system replaces specialized hardware mechanisms (depth-detecting cameras, infrared sensors) with software-based analysis of standard camera images. By using image processing and machine learning to analyze facial movements and characteristics, the system achieves accurate liveness detection without complex hardware.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Measurement precision

If comprehensive facial scanning is performed, then authentication accuracy is improved, but processing time increases

Engineering Contradiction:
Improveauthentication accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs partial facial scanning by focusing on key facial regions and characteristics necessary for both recognition and liveness detection. Rather than scanning every detail of the face, the system analyzes specific features (eye movement, facial muscle movements, depth information) that are sufficient for accurate authentication and liveness verification, reducing processing time while maintaining accuracy.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP3862897B1Facial recognition for user authentication
Publication Date: 2024.03.06 FAIR ISAAC & CO INC
  • EP3862897B1 patent drawingFigure 1
  • EP3862897B1 patent drawingFigure 2
  • EP3862897B1 patent drawingFigure 3A~3B

AI summary

Systems and methods for utilizing an image capture device to scan facial features of a user, responsive to recognition of a plurality of beam projection points on the face of the user. The first data captured from scanning the facial features may be authenticated against a facial depth map stored as a data structure in a data storage medium. In response to successful authentication, the facial features of the user may be continually scanned to detect facial movements indicative of the user's liveness. Access may be granted to the user, in response to verifying the user's liveness.