Biometric Adaptation via Standard Deviation Correction Factors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Biometric systems often falsely reject users with unstable or unreliable biometric data, leading to increased rejection rates for certain groups, such as older individuals or those with medical conditions affecting their voice or fingerprints.
Innovation Solution
A method is introduced to adapt biometric systems by extracting features from user samples during enrollment, calculating standard deviations, and deriving correction factors based on a trend line of a match score vs. standard deviation density function, which are then applied to modify verification scores, allowing for more accurate identification of reliable users while minimizing impact on overall system accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If biometric systems use standard verification thresholds, then system reliability is maintained, but users with unstable biometric data are falsely rejected
Solution Approach 1:
The patent applies parameter changes by calculating a correction factor based on the standard deviation of the biometric feature and using this to adjust the verification threshold dynamically. When the standard deviation exceeds a threshold, indicating unstable biometric data, the system modifies the verification threshold to accommodate this variability, thereby reducing false rejections while maintaining security.
Solution Approach 2:
The verification threshold is made dynamic rather than fixed. The system calculates a correction factor that depends on the standard deviation of the biometric feature, and uses this to adjust the threshold in real-time during verification. This dynamic adjustment allows the system to adapt to users with unstable biometric characteristics without compromising overall system reliability.
2Adaptability or versatility
If correction factors are applied to adjust match scores, then acceptance rate for users with unstable features improves, but system complexity increases
Solution Approach 1:
The correction factor is calculated during the enrollment phase before verification occurs. By pre-computing the standard deviation and deriving the correction factor at enrollment time, the system avoids complex calculations during the verification phase, thereby reducing operational complexity while still providing adapted verification for users with unstable biometric data.
Solution Approach 2:
The system automatically calculates and applies correction factors based on the inherent characteristics of each user's biometric data during enrollment. This self-service mechanism requires minimal manual intervention or configuration, as the system derives correction factors autonomously from the biometric samples provided during enrollment, thereby limiting the increase in system complexity.
Data Source
AI summary
Embodiments of a system and method for verifying an identity of a claimant are described. In accordance with one embodiment, a feature may be extracted from a biometric sample captured from a claimant claiming an identity. The extracted feature may be compared to a template associated with the identity to determine the similarity between the extracted feature and the template with the similarity between them being represented by a score. A determination may be made to determine whether the identity has a correction factor associated therewith. If the identity is determined to have a correction factor associated therewith, then the score may be modified using the correction factor. The score may then be compared to a threshold to determine whether to accept the claimant as the identity. In accordance with a further embodiment, during enrollment of a subject in a biometric verification system, a feature may be extracted from a biometric sample captured from the subject requesting enrollment and a standard deviation for the feature may then be calculated. A determination may then be performed to determining whether the standard deviation of the feature is greater than a standard deviation of a centroid of a density function. If the standard deviation of the feature is greater than the standard deviation of the centroid, then a correction factor for the subject may be derived based on a trend line of the density function.