Biometric Authentication Using Personalized Identifiers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current biometric authentication systems for financial transactions are cumbersome and prone to false matches, especially when dealing with large user bases, as they rely on generic algorithms and require users to remember multiple account details, leading to inefficiencies and security concerns.
Innovation Solution
A system that uses personalized identifiers combined with biometric samples, such as voice or handwriting, to create unique records with associated models, allowing for privileged access and real-time recalibration of models to prevent ambiguity and improve authentication accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If generic biometric algorithms are used for authentication in large user bases, then system complexity is reduced, but measurement precision deteriorates due to false matches
Solution Approach 1:
The authentication system is segmented into two distinct phases: identification phase where personalized identifiers are used to narrow down potential users, and authentication phase where biometric verification confirms identity. This segmentation allows generic algorithms to handle the large user base efficiently while personalized models ensure high precision for individual authentication.
Solution Approach 2:
Personalized identifier models are created and stored in advance during user registration. These pre-computed models enable the system to quickly filter and identify potential users before biometric verification, reducing the computational burden during actual authentication while maintaining high accuracy.
2Reliability
If multiple account details are required for authentication, then security is improved, but ease of operation deteriorates due to user burden
Solution Approach 1:
The system merges the identification function and authentication function into a unified process. Personalized identifiers serve dual purposes: they act as memorable user-friendly identifiers and simultaneously function as authentication credentials when combined with biometric verification, eliminating the need for separate passwords or PINs.
Solution Approach 2:
Users create their own personalized identifiers based on their own information during registration, making the identifiers inherently memorable and easy to use. The system then uses these self-created identifiers for both identification and authentication purposes, reducing operational burden while maintaining security.
3Measurement precision
If personalized identifiers are used for each user, then measurement precision is improved for authentication, but device complexity increases due to model management
Solution Approach 1:
Personalized identifier models are computed and stored in advance during user registration, before actual authentication occurs. This preliminary computation transforms complex biometric data into pre-processed models that can be efficiently compared during authentication, reducing real-time computational complexity while maintaining high precision.
Solution Approach 2:
The system extracts essential features from raw biometric data during registration and stores only these extracted features as personalized identifier models. This extraction reduces the complexity of storing and processing complete biometric datasets while preserving the essential information needed for accurate authentication.
4Reliability
If strict uniqueness is enforced for account identifiers, then reliability is improved, but ease of manufacture deteriorates due to user constraints
Solution Approach 1:
Users autonomously create their own personalized identifiers during registration based on their personal information or preferences. The system automatically manages uniqueness through the identification process, allowing users complete freedom in identifier creation without manual enforcement of uniqueness constraints, thus improving both ease of creation and reliability.
Data Source
AI summary
Disclosed is a system and method for biometric authentication of a user using a personalised identification and associated biometric data. In one embodiment, a plurality of personalised identifiers and biometric data may be captured from a number of users and stored in a repository as stored records. The authentication process may be divided into two phases. In the first phase, either a speech recognition or character recognition process may be applied in order to determine the text spoken or written by the user. Subsequently a few records may be fetched from the repository on the basis of text mapping. In the second phase, biometric authentication may be performed by comparing the biometric sample with the stored biometric data corresponding to the fetched records to uniquely identify a single user. Further a machine learning technique may be applied in order to periodically refine a plurality of models stored in the repository.