Biometric Recognition System Using Distributed Template Segments
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional distributed biometric information management systems face challenges in maintaining high recognition accuracy while reducing the amount of data to be transmitted during biometric recognition, due to increased network load from large data transmission.
Innovation Solution
The method involves generating biometric information segments by dividing extracted user data, calculating distances between pre-stored template segments in multiple databases, and detecting matching templates using these distances, thereby reducing data transmission and maintaining recognition accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If biometric information template segments distributed in multiple databases are transmitted to perform recognition, then recognition accuracy is maintained, but network load increases due to large data transmission
Solution Approach 1:
The patent extracts only the essential recognition features from the distributed biometric template segments, transmitting only these extracted features rather than the complete segments. This extraction process maintains the core information needed for accurate recognition while eliminating redundant data, thereby reducing network transmission load while preserving recognition accuracy.
Solution Approach 2:
The patent transforms the biometric template segments by changing their representation parameters - converting complete template segments into compressed feature vectors or extracted characteristics. This parameter transformation maintains the discriminative power needed for recognition while significantly reducing the data volume that needs to be transmitted across the network.
2Reliability
If biometric information is divided and stored in multiple databases, then personal information security is improved, but system complexity increases
Solution Approach 1:
The patent divides the biometric information system into multiple independent database segments, each storing only partial template segments. This segmentation ensures that no single database contains complete biometric information, thereby improving security. The segmentation is structured so that each segment is independently manageable, which actually simplifies system operations compared to managing a single large database.
Solution Approach 2:
The patent creates a universal recognition framework that can operate across multiple distributed databases with standardized interfaces and protocols. This multi-functional architecture allows the same recognition process to work regardless of how the data is distributed, reducing the operational complexity that would otherwise arise from managing multiple different systems.
3Measurement precision
If all biometric template segments are transmitted for recognition, then recognition accuracy is maintained, but transmission time increases
Solution Approach 1:
The patent extracts only the most discriminative and essential features from the biometric template segments before transmission. By identifying and transmitting only these critical features rather than complete segments, the system maintains recognition accuracy while dramatically reducing the time required for data transmission across the network.
Solution Approach 2:
The patent transmits a partial set of biometric features that is sufficient for accurate recognition without being excessive. This partial action approach identifies the minimum necessary data subset required for reliable recognition, avoiding the time cost of transmitting complete template segments while ensuring recognition accuracy is not compromised.
Data Source
AI summary
A method for performing biometric recognition in a system in which biometric information is distributed and stored in a plurality of databases includes extracting biometric information of a user, generating a plurality of biometric information segments by dividing the extracted biometric information, calculating distances between pre-stored biometric information template segments for each of the plurality of databases and a corresponding one of the plurality of biometric information segments, and detecting a biometric information template matching the biometric information by using the calculated distances.