Dynamic Face Authentication Criterion Adjustment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing face authentication systems face challenges in setting suitable criteria to minimize errors such as erroneous acceptance or rejection, particularly when multiple authentications are performed, affecting authentication accuracy.
Innovation Solution
A face authentication system that dynamically sets criteria based on the state of the access target system, using a criterion setting unit to adjust authentication thresholds according to different system states, such as login, learning, or testing, to optimize accuracy and prevent impersonation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a fixed authentication criterion is used for all face authentication operations, then the system is simple to operate, but authentication accuracy deteriorates due to erroneous acceptance or rejection
Solution Approach 1:
The patent applies dynamics by making the authentication criterion adjustable rather than fixed. The criterion setting unit dynamically changes authentication thresholds based on the access target system's state, allowing the system to adapt between different operational contexts (e.g., login vs. learning phases) to optimize authentication accuracy for each state.
Solution Approach 2:
The patent implements parameter changes by modifying authentication criterion parameters according to system state. The criterion setting unit adjusts specific authentication parameters (such as threshold values) based on whether the system is in login mode, learning mode, or other states, thereby improving authentication accuracy without requiring complete system redesign.
2Reliability
If a strict authentication criterion is used, then erroneous acceptance of wrong persons is reduced, but erroneous rejection of correct persons increases
Solution Approach 1:
The system dynamically adjusts authentication strictness based on the current state. During login operations, stricter criteria are applied to ensure high reliability and prevent unauthorized access. During learning or less critical operations, the criterion setting unit relaxes the authentication threshold, maintaining reliability while improving user convenience and reducing erroneous rejections.
Solution Approach 2:
Different authentication criterion qualities are applied to different operational contexts. The patent implements local quality by having the criterion setting unit select appropriate authentication strictness levels for specific system states (login vs. learning), ensuring high reliability where needed while maintaining ease of operation where appropriate.
3Reliability
If multiple face authentication operations are performed, then authentication security is improved, but the accumulation of errors increases without proper criterion adjustment
Solution Approach 1:
The system implements feedback by having the criterion setting unit continuously monitor the access target system's state and adjust authentication criteria accordingly. This feedback mechanism ensures that after multiple authentication operations, the system can adapt its criterion to maintain both security and accuracy, preventing error accumulation by resetting or adjusting thresholds based on current operational context.
Data Source
AI summary
According to at least one example embodiment of the present invention, provided is a face authentication system including: a criterion setting unit that sets a criterion of face authentication performed on a user so as to be different in accordance with a state of an access target system accessed by the user; and a face authentication unit that performs face authentication of the user based on the criterion.