Biometric Processor Ear Data Fusion Weighted Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Biometric algorithms face challenges in achieving a balance between low false acceptance and false rejection rates, as these rates are inter-dependent, making it difficult to provide both secure and reliable authentication using ear biometric data.
Innovation Solution
A biometric processor that combines ear biometric data from both ears using weighted scores, where the weights are configured based on the discriminative properties of each ear to emphasize the more discriminative ear, and applies a polynomial transform followed by a nonlinear function to generate an overall biometric score.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the authentication threshold is lowered to reduce false rejection rate, then reliable authentication for authorised users is improved, but false acceptance rate increases compromising security
Solution Approach 1:
The patent segments the biometric authentication process by separating the authentication decision into two independent stages: (1) a preliminary check using a lower threshold to identify potential matches, and (2) a final verification using a higher threshold to confirm authentication. This segmentation allows the system to prioritize reliable identification in the first stage while maintaining security through the stricter second stage, thereby reducing false rejections without compromising security.
Solution Approach 2:
The patent applies dynamic thresholding by using different threshold values for different stages of authentication. The first threshold (lower) is used for initial matching to maximize sensitivity and reduce false rejections, while the second threshold (higher) is used for final verification to ensure security and minimize false acceptances. This dynamic adjustment of thresholds based on the authentication stage resolves the contradiction between reliability and security.
2Object-affected harmful factors
If the authentication threshold is raised to reduce false acceptance rate, then security is improved, but false rejection rate increases making authentication frustrating for authorised users
Solution Approach 1:
The authentication process is segmented into two stages with different threshold requirements. The first stage uses a lower threshold to cast a wide net and identify potential matches, reducing false rejections. The second stage then applies a higher threshold to verify the identity, ensuring security and minimizing false acceptances. This segmentation allows the system to achieve both low false acceptance rate and low false rejection rate.
Solution Approach 2:
The system dynamically adjusts the authentication threshold based on the current stage of verification. By using a lower threshold in the first stage and a higher threshold in the second stage, the system adapts its stringency to the operational requirements of each stage, thereby reducing false acceptances while maintaining high reliability in identification.
3Ease of operation
If a single threshold is used for authentication, then the system is simple to operate, but it cannot simultaneously achieve low false acceptance and false rejection rates
Solution Approach 1:
The patent segments the authentication threshold into two distinct values: a first threshold for preliminary matching and a second threshold for final verification. This segmentation allows the system to achieve lower equal error rates by optimizing each threshold for its specific function, while the overall process remains intuitive and easy to operate as a two-step verification mechanism.
Solution Approach 2:
The system changes the threshold parameter dynamically based on the authentication stage. By transitioning from a lower threshold in the first stage to a higher threshold in the second stage, the system optimizes its performance to achieve low false acceptance and false rejection rates simultaneously, while maintaining operational simplicity through automated threshold switching.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach improves the efficacy of the biometric process by reducing the equal error rate, enhancing the ability to accurately authenticate users while minimizing false rejections and acceptances.
Implementation Method 1
The ear canal is a resonant system, and therefore one feature which may be extracted from the response signal is the resonant frequency of the ear canal
Implementation Method 2
One or more loudspeakers or similar transducers positioned close to or within the ear generate a stimulus, and one or more microphones similarly positioned close to or within the ear detect the response of the ear to the stimulus
Data Source
AI summary
A biometric processor comprises: one or more inputs configured to receive first ear biometric data acquired in respect of a first ear of a user and second ear biometric data acquired in respect of a second ear of the user; a processing module configured to perform a biometric algorithm on the first ear biometric data and the second ear biometric data, based on a comparison of the first ear biometric data to a first stored ear biometric template for an authorised user and a comparison of the second ear biometric data to a second stored ear biometric template for the authorised user, to obtain respective first and second biometric scores; a fusion module configured to apply first and second weights to the respective first and second biometric scores to obtain first and second weighted biometric scores, and to combine at least the first and second weighted biometric scores to generate an overall biometric score, wherein the first and second weights are different to each other; and wherein a biometric result is based on the overall biometric score.