Passive Liveness Verification via Image Diffusion and Color 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, necessitating a method for passive-subject liveness verification to prevent spoofing without physical movement.
Innovation Solution
A system that preprocesses images or videos for imperative and dynamic analysis using non-machine learning and machine learning methodologies, respectively, 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 required for liveness verification, then spoofing prevention is improved, but subject cooperation and ease of operation deteriorate
Solution Approach 1:
The system performs self-service by automatically analyzing passive images for liveness indicators without requiring the subject to perform any actions. The algorithm independently evaluates diffusion speed, color variance, contour characteristics, and other parameters to determine liveness, eliminating the need for subject cooperation while maintaining spoofing prevention.
Solution Approach 2:
The patent replaces the mechanical interaction system (where subjects physically perform actions like blinking or smiling) with an optical analysis system that evaluates passive image characteristics. By substituting physical interaction with computational analysis of image properties like diffusion speed and color variance, the system achieves both spoofing prevention and ease of operation.
2Measurement precision
If physical movement is required for liveness verification, then liveness detection accuracy is improved, but user comfort and privacy deteriorate
Solution Approach 1:
The system changes the parameters being measured from dynamic physical movements to static image characteristics. Instead of requiring subjects to move, the algorithm analyzes parameters inherent in still images such as diffusion speed, color variance, contour smoothness, and specularity, achieving accurate liveness detection without compromising user comfort or privacy.
Solution Approach 2:
The analysis system performs self-service evaluation by automatically extracting liveness indicators from passive images without requiring subject participation. The algorithm independently assesses multiple parameters including diffusion speed and color variance to determine liveness, maintaining detection accuracy while preserving user comfort and privacy.
3Reliability
If active subject interaction is implemented, then liveness verification reliability is improved, but time consumption increases
Solution Approach 1:
The system performs preliminary action by analyzing passive images immediately upon capture without requiring subsequent physical interactions. All liveness verification parameters (diffusion speed, color variance, contours) are evaluated in a single processing step, eliminating the time required for explaining and executing physical actions while maintaining verification reliability.
Solution Approach 2:
The verification system operates autonomously by automatically analyzing passive images for liveness indicators without requiring subject participation. The algorithm independently evaluates multiple parameters and makes verification decisions, achieving both high reliability and minimal time consumption by eliminating interactive requirements.
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.