Masked Biometric Code Generation for Stable Bitwise Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Biometric systems face challenges in achieving stable and repeatable binary codes under non-ideal conditions, leading to high false rejection and acceptance rates, and require high-quality data capture environments, which limits their usability in common-use cases.
Innovation Solution
A method and system for generating a masked biometric code using a validity mask to create a stable and repeatable code from biometric data, allowing bitwise comparison and reducing false rejection and acceptance rates, even under varying capture conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If biometric systems use traditional binary code comparison methods, then they can achieve simple implementation, but they produce high false rejection and acceptance rates under non-ideal conditions
Solution Approach 1:
The biometric code is segmented into multiple individual bit positions, each independently evaluated for stability. The system divides the code into stable bits (that repeat consistently) and unstable bits (that vary under non-ideal conditions), allowing selective processing of each segment to improve overall reliability.
Solution Approach 2:
Different processing approaches are applied to different parts of the biometric code. Stable bits are processed with strict matching requirements, while unstable bits are processed with more flexible matching criteria. This local differentiation optimizes the balance between security and acceptance rates.
2Reliability
If biometric systems require high-quality data capture environments, then they can achieve stable and repeatable codes, but they limit usability in common-use cases
Solution Approach 1:
The system dynamically adjusts its processing based on the quality and stability of the captured biometric data. It identifies which bits are stable and which are unstable in real-time, adapting the matching criteria accordingly. This allows the system to maintain reliability across varying capture conditions without requiring controlled environments.
Solution Approach 2:
The system changes the parameters of code comparison based on the stability characteristics of the captured data. By modifying matching thresholds and criteria dynamically, it achieves stable code comparison results even when capture conditions vary, thereby improving adaptability to common-use scenarios.
3Adaptability or versatility
If biometric systems use distance metrics such as Hamming distance, then they can accommodate non-ideal conditions, but they cannot reproduce a strictly individual binary code required for cryptography
Solution Approach 1:
The code is segmented into stable and unstable bit positions. For cryptographic applications requiring exact reproducibility, the system uses only the stable bits that can be exactly reproduced. The unstable bits are handled separately with tolerance, allowing the system to satisfy both cryptographic requirements and non-ideal condition tolerance.
Solution Approach 2:
Different quality requirements are applied to different parts of the code. Stable bits are processed with exact matching for cryptographic precision, while unstable bits are processed with distance metrics for tolerance to non-ideal conditions. This local quality differentiation resolves the contradiction between precision and adaptability.
4Reliability
If biometric systems store encrypted biometric data for comparison, then they can maintain security, but they create vulnerability to hacking of stored data
Solution Approach 1:
The system extracts and removes the vulnerable stored biometric data from the system. Instead of storing encrypted biometric templates for comparison, it uses a method that generates comparison codes on-demand from the captured biometric data, eliminating the stored data that could be hacked while maintaining security through the stable code generation process.
Data Source
Figure 1
Figure 2
Figure 3A~3C
AI summary
Biometric data such as iris, facial, or fingerprint data may be obtained from a user. A public code may be generated from the biometric data, but does not obtain any of the biometric data or information that can be used to identify the user. The public code includes information that can be used to extract from the biometric data a biometric code that is suitable for bitwise comparison. Neither the underlying biometric data nor information from which the biometric data may be determined is stored as only the public code and the actual biometric feature of the user is required to generate the biometric code.