Biometric Template Screening Using Segmented Feature Sets
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Fingerprint-based biometric security systems face challenges in maintaining a high security level without degrading system performance due to inverse relationships between false acceptance and rejection rates, especially when multiple biometric entries are enrolled from different sources, leading to increased comparisons and resource usage.
Innovation Solution
A method that utilizes two distinct feature sets for fingerprint biometric templates: a first feature set for initial screening and a second feature set for more intensive matching, where the first set includes spatially dependent features like minutia points and the second set includes pattern-dependent features like minutia types, allowing for efficient identification and authentication without compromising security or performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple biometric entries are enrolled from a single user to improve security coverage, then the system can handle more authentication scenarios, but the false acceptance rate increases and effective security level decreases
Solution Approach 1:
The patent segments the biometric template into multiple independent feature sets (e.g., minutiae features, ridge features, pore features). Each feature set can be independently compared during authentication. This segmentation allows the system to evaluate multiple biometric entries without linearly increasing false acceptance risk, as each feature set provides independent verification dimensions.
Solution Approach 2:
The patent changes the parameter of template representation by using multiple distinct feature sets instead of a single comprehensive template. Each feature set captures different aspects of the biometric data with different characteristics. This parameter change enables the system to maintain security by requiring consistent matches across multiple feature dimensions rather than relying on a single template comparison.
2Reliability
If the false acceptance rate is decreased to increase security level, then system security improves, but the false rejection rate increases and system performance degrades
Solution Approach 1:
The patent divides the authentication process into multiple independent feature set comparisons. Each feature set can be configured with appropriate threshold settings optimized for its specific characteristics. This segmentation allows the system to achieve high security through multiple independent verification stages without forcing a single high threshold that would cause excessive false rejections.
Solution Approach 2:
The patent performs comparisons on multiple feature sets, which is more than a single template comparison. By requiring matches across multiple feature sets rather than relying on a single comparison, the system achieves higher security confidence without needing to set excessively high thresholds on individual comparisons that would degrade performance.
3Quantity of substance
If more users are added to the system to increase system capacity, then user base grows, but the number of comparisons required increases and system performance degrades
Solution Approach 1:
The patent segments the authentication process into multiple independent feature set comparisons. This segmentation enables more efficient processing by allowing parallel evaluation of different feature dimensions. The modular structure of comparing independent feature sets reduces the computational burden per user and scales more efficiently as the user base grows.
Solution Approach 2:
The patent performs preliminary comparisons on multiple feature sets to quickly identify potential matches before conducting more intensive verification. This preliminary action on segmented features allows the system to efficiently handle large user bases by filtering candidates early in the authentication process using the independent feature sets.
Data Source
AI summary
A method, system and computer program product which allows identification of an enrollment biometric template having a highest probability of matching a sample biometric template from a plurality of enrolled biometric templates without compromising or significantly compromising system security. In one embodiment of the invention, first feature set information is derived from sample and enrollment biometric templates. The first feature set information generally comprises spatially dependent information associated with a fingerprint. The first feature set information is then used to determine which enrollment biometric template has the highest probability of matching the sample biometric template. Second feature set information is then derived from the biometric sample template and the determined enrollment biometric template and used to perform a one-to-one match. The second feature set information generally comprises pattern dependent information associated with a fingerprint.