Biometric Authentication Database Segmentation for Speed and Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Biometric authentication systems face slowness and increased authentication errors when dealing with a large number of individuals, as the verification process becomes slower and more prone to errors due to the need for numerous comparisons among a vast number of referenced individuals.
Innovation Solution
The method distributes reference information across multiple sub-databases, using addressing information provided by the individual to narrow down the search to a specific subset, thereby reducing the number of comparisons and minimizing errors by strategically selecting sub-databases based on distance criteria and utilizing biometric information for secure authentication.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the system stores reference information for a very large number of individuals in a single database, then the system can authenticate any individual, but the authentication process becomes slow and the risk of errors increases
Solution Approach 1:
The patent divides the large reference database into multiple sub-databases (first sub-database, second sub-database, etc.). Each sub-database stores reference information for a specific subset of individuals. This segmentation reduces the number of comparisons needed during authentication, as the system only needs to search within the relevant sub-database identified by the addressing information, rather than searching through all reference information in a single large database.
Solution Approach 2:
The patent introduces addressing information (such as a code or identifier) as an intermediary element that links the individual to their specific sub-database. This addressing information acts as a mediator that guides the authentication process directly to the relevant subset of reference information, eliminating the need to search through the entire database and significantly reducing authentication time while maintaining accuracy.
2Adaptability or versatility
If the system stores reference information for a very large number of individuals, then the system can authenticate any individual, but the number of comparisons increases leading to more authentication errors
Solution Approach 1:
By segmenting the reference database into multiple sub-databases, the patent reduces the density of reference information in each sub-database. This segmentation ensures that even as the total system capacity grows to accommodate more individuals, each sub-database maintains a manageable size, reducing the probability of authentication errors caused by having too many similar biometric templates in a single search space.
Solution Approach 2:
The addressing information serves as an intermediary that accurately directs the authentication process to the correct sub-database containing the individual's reference information. This mediator ensures that the system maintains high adaptability and versatility by scaling to accommodate many individuals, while simultaneously maintaining reliability by preventing erroneous comparisons through precise sub-database identification.
3Reliability
If the system performs comprehensive biometric comparisons to ensure accurate authentication, then authentication accuracy is maintained, but the processing time increases significantly
Solution Approach 1:
The patent segments the authentication process into two stages: first, identifying the relevant sub-database using addressing information; second, performing biometric comparisons only within that specific sub-database. This segmentation maintains authentication accuracy by ensuring comprehensive comparisons are performed within the correct subset, while dramatically improving productivity by eliminating unnecessary comparisons with unrelated individuals in a large database.
Solution Approach 2:
The addressing information acts as an intermediary that enables the system to quickly narrow down the search space before performing detailed biometric comparisons. This mediator allows the system to maintain high authentication accuracy through thorough comparisons while achieving high throughput by avoiding the time-consuming process of searching through an entire large database when only a small subset needs to be examined.
Data Source
AI summary
A biometric authentication method if provided for an individual to be authenticated amongst a very large quantity of individuals with an authentication system storing a set of reference information each associated to one of the individuals. The reference information is distributed across a plurality of sub-databases. The method includes a phase of adding reference information representative of a new individual, including selecting the sub-database that is best adapted to store the reference information to be added. A phase of authentication includes: provision by the individual of authentication biometric information and of an identifier forming addressing information, designating at least one of said sub-databases likely to contain the reference information representative of said individual; and searching amongst the reference information stored by the authentication system, of reference information corresponding to the individual, the searching being carried out on a subset of said set of reference information, identified by the addressing information.