Passive Liveness Verification via Optical Field Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing biometric security systems rely on active interactions to verify liveness, which can be tricked or deemed awkward, leading to a need for a method that provides passive-subject liveness verification to prevent spoofing without physical movement.
Innovation Solution
A system that preprocesses images or videos for analysis using both non-machine learning (imperative analysis) and machine learning (dynamic analysis) methodologies to determine liveness without subject interaction, analyzing factors like color variance, contour detection, diffusion speed, blurriness, specularity, and gamut differences to verify if an image is of a live individual.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If active interactions are used to verify liveness, then liveness verification capability is improved, but ease of operation deteriorates and susceptibility to spoofing increases
Solution Approach 1:
The patent replaces active mechanical interactions (requiring subject to perform physical actions like winking or waving) with passive optical field analysis (analyzing intrinsic properties of light reflection, diffusion, and absorption in the captured image). This substitution eliminates the need for subject participation while maintaining liveness verification capability through analysis of physiological characteristics such as skin texture, subsurface scattering, and optical properties that are inherently present in live subjects but absent in spoofing materials.
2Reliability
If active interactions are used to verify liveness, then liveness verification capability is improved, but susceptibility to spoofing increases
Solution Approach 1:
The patent changes the verification parameters from behavioral parameters (subject performing actions) to optical-physical parameters (light interaction characteristics). By analyzing parameters such as diffusion speed, blurriness, specularity, and gamut differences that reflect the physical properties of living tissue, the system creates a verification mechanism that is inherently resistant to spoofing since these optical properties cannot be replicated by photographs, 3D representations, or digital renderings.
3Ease of operation
If passive-subject verification is used, then ease of operation is improved, but measurement precision deteriorates
Solution Approach 1:
The patent segments the liveness verification process into multiple independent analysis components: diffusion speed analysis, blurriness analysis, specularity analysis, and gamut differences analysis. Each segment focuses on a specific optical property, allowing the system to gather multiple lines of evidence from passive image data. This segmentation enables comprehensive verification without requiring active subject participation, maintaining both ease of operation and measurement precision through cumulative analysis of multiple parameters.
Data Source
AI summary
The present system may be deployed in various scenarios to provide proof of liveness (also referred to herein as “liveness verification”) of an image without interaction of the subject of the image. The liveness verification process generally comprises imperative analysis and dynamic analysis of the image, after which liveness of the image may be determined.