Face Liveness Detection via Multi-View Image Variance Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing facial biometric recognition systems are vulnerable to spoofing attacks, including those using static images and videos, and lack adequate protection without specialized equipment while maintaining user convenience.
Innovation Solution
A method and system that capture multiple face images from different viewpoints over time, verifying liveness by comparing consistency and variance in facial expressions and orientations, using standard digital cameras to prevent unauthorized access.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple face images are captured and compared from different viewpoints over time, then security against spoofing attacks is improved, but device complexity increases
Solution Approach 1:
The system segments the authentication process into multiple independent steps: capturing images from different viewpoints, comparing consistency between images, detecting liveness, and performing final authentication. This segmentation allows each component to be simpler while the collective system achieves high security.
Solution Approach 2:
The system performs preliminary actions by capturing multiple face images from different viewpoints before the final authentication decision. This preliminary capture and comparison of images establishes a baseline for consistency checking, enabling more reliable spoofing detection without requiring complex real-time analysis during the critical authentication moment.
2Reliability
If dynamic image capturing requiring user motion is implemented, then protection against static image spoofing is improved, but ease of operation deteriorates
Solution Approach 1:
The system employs dynamics by requiring the user to change their facial expression or head orientation between the first and second time periods. This dynamic element ensures the user is alive and present, yet the system accommodates natural human movement patterns, maintaining ease of operation while achieving spoofing protection.
Solution Approach 2:
The system changes parameters by comparing facial characteristics (expression, orientation, position) across different time periods. By monitoring these parameter changes and verifying they are consistent with natural human behavior, the system achieves security without requiring complex or unnatural user actions.
3Measurement precision
If three-dimensional face detection using specialized cameras and light-emitting devices is used, then detection precision is improved, but device complexity and cost increase
Solution Approach 1:
The system achieves three-dimensional face detection capabilities using standard digital cameras that are already present in most devices. By capturing images from multiple viewpoints and using computational methods to analyze consistency and detect liveness, the system provides 3D detection precision without requiring specialized expensive hardware.
Solution Approach 2:
Instead of using specialized 3D cameras, the system creates a computational model of the three-dimensional face by capturing multiple two-dimensional images from different viewpoints and analyzing their consistency. This copying approach reconstructs 3D information through software rather than requiring specialized 3D sensing hardware.
Data Source
AI summary
Technologies are provided for assessing liveness of a subject presented to a set of one or more cameras. A first image and a second image depicting a face are captured during a first time period, and a third image and a fourth image depicting the face are captured during a second time period. A first variance in facial appearance is detected between the first depiction of the face and the third depiction of the face, and a second variance in facial appearance is detected between the second depiction of the face and the fourth depiction of the face. A liveliness of a person is verified based on a determination that the first variance in facial appearance corresponds in time to the second variance in facial appearance.