Passive 3D Face Imaging Dual-Level Macro-Micro Authentication
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional face ID systems in electronic devices are prone to spoofing and offer inadequate security due to reliance on limited large-scale facial structures, often prioritizing speed over accuracy, leading to false positives and resource inefficiencies.
Innovation Solution
Implementing passive three-dimensional face imaging that captures deterministic macro-structure and micro-structure measurements, using a dual-level authentication process involving macro-structure and micro-structure image sizing to enhance security without excessive resource consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional face ID systems use limited large-scale facial structures for identification, then processing speed and resource efficiency are improved, but security and anti-spoofing capability deteriorate
Solution Approach 1:
The patent divides facial structure analysis into two distinct segments: macro-structure analysis (large-scale features like eye position, nose shape, mouth location) and micro-structure analysis (fine-scale features like skin texture, pore patterns, fine wrinkles). This segmentation allows the system to process macro-structures quickly for initial identification while using micro-structures for security verification, resolving the contradiction between speed and security by handling different structural levels separately with appropriate processing priorities.
2Ease of operation
If conventional face ID systems prioritize rapid authentication, then user convenience is improved, but false positive rate increases
Solution Approach 1:
The system performs preliminary macro-structure analysis first to quickly determine if the presented face matches the registered user's overall facial geometry. Only when macro-structure matching succeeds does the system proceed to micro-structure verification. This preliminary action filters out obvious mismatches quickly (maintaining convenience) while ensuring that only potentially valid authentications undergo the more time-consuming micro-structure analysis (improving accuracy).
Solution Approach 2:
The patent transitions from two-dimensional facial recognition (relying solely on macro-structural landmarks) to three-dimensional analysis by incorporating micro-structural depth information such as skin texture variations, pore distributions, and fine surface topography. This dimensional expansion provides an additional verification layer that significantly reduces false positives while maintaining rapid authentication through the hierarchical processing approach.
3Use of energy by moving object
If conventional face ID systems use simple recognition algorithms, then resource consumption is reduced, but susceptibility to spoofing increases
Solution Approach 1:
The patent extracts and isolates micro-structural features (skin texture, pore patterns, fine wrinkles) as separate verification elements distinct from macro-structural facial landmarks. By extracting these fine-scale features and analyzing them independently, the system creates a security layer that is computationally efficient yet highly resistant to spoofing, as spoofing materials cannot replicate micro-structural details. This extraction approach maintains low resource consumption while dramatically improving anti-spoofing capability.
Data Source
AI summary
Techniques are described for passive three-dimensional (3D) face imaging based on macro-structure and micro-structure image sizing, such as for biometric facial recognition. A set of images of a user's face is processed to extract authentication deterministic macro-structure (DMAS) measurements. A database includes profile DMAS measurements, profile location definitions for deterministic micro-structure (DMIS) feature regions, and profile DMIS signatures computed for the DMIS feature regions. A first-level authentication determination can be based on comparing the authentication DMAS measurements with the profile DMAS measurements. Authentication DMIS signatures can be computed from sub-images obtained for the DMIS feature regions at the profile location definitions. A second-level authentication determination can be based on comparing the authentication DMIS signatures with the profile DMIS signatures. An authentication result can be output based on both the first-level authentication determination and the second-level authentication that indicates whether authentication of the user is granted or denied.