Face Collation Apparatus Dynamic Threshold Adjustment

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Face collation apparatuses experience fluctuations in authentication accuracy due to varying registration and collation conditions, leading to inconsistent stranger acceptance rates, which requires burdensome adjustments each time the apparatus is installed.

Innovation Solution

A face collation apparatus that adjusts scores or thresholds using specific parameters to maintain constant stranger acceptance and principal rejection rates regardless of registration and collation conditions, utilizing score or threshold adjustment parameters to stabilize authentication accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If the number of registrants increases, then the coverage of the face collation apparatus improves, but the stranger acceptance rate increases and authentication accuracy fluctuates

Engineering Contradiction:
Improvecoverage of face collation apparatusVSAvoidauthentication accuracy
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The patent applies parameter changes by dynamically adjusting the threshold parameter based on the number of registrants. When the number of registrants increases, the threshold is automatically adjusted to maintain stable authentication accuracy. This resolves the contradiction by changing the threshold parameter to compensate for the increased likelihood of strangers resembling registrants, thereby maintaining reliability while allowing adaptability to increase.

Inventive Principle:
Principle #35Parameter changes

2Reliability

If ex-ante adjustment is performed every time the apparatus is installed, then authentication accuracy stability improves, but user burden and operational complexity increase

Engineering Contradiction:
Improveauthentication accuracy stabilityVSAvoiduser burden during installation
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The patent implements self-service by enabling the apparatus to automatically adjust its own threshold parameter based on the detected number of registrants without requiring user intervention. The system autonomously performs the adjustment that would otherwise need to be done manually during installation, thereby maintaining authentication accuracy stability while eliminating the operational burden on users.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent applies dynamics by making the threshold parameter dynamic rather than static. The threshold automatically changes based on the number of registrants detected in the environment, allowing the system to adapt to different installation scenarios without manual reconfiguration. This dynamic adjustment mechanism maintains reliability while simplifying operation.

Inventive Principle:
Principle #15Dynamics

3Device complexity

If a single threshold is used for all conditions, then device complexity is reduced, but authentication accuracy fluctuates with registration and collation conditions

Engineering Contradiction:
Improvethreshold management complexityVSAvoidauthentication accuracy consistency
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The patent resolves this contradiction by dynamically changing the threshold parameter based on detected conditions such as the number of registrants. Rather than using a fixed threshold that works for all conditions, the system automatically adjusts the threshold parameter to match the current operational context, thereby maintaining consistent authentication accuracy without requiring complex manual configuration for each condition.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS8320642B2Face collation apparatus
Publication Date: 2012.11.27 OMRON CORP
  • US8320642B2 patent drawing
  • US8320642B2 patent drawing
  • US8320642B2 patent drawing

AI summary

A face collation apparatus has a storage that stores a feature quantity of at least one registrant, the feature quantity being extracted from a registration image of the registrant, a feature quantity extractor that extracts a feature quantity from a collation image of a collation object person, a score calculator that calculates a score indicating an analogy degree between the feature quantity of the registrant and the feature quantity of the collation object person, a score adjuster that adjusts the score using a score adjustment parameter so that any one of a stranger acceptance rate indicating a probability that a stranger is accepted at the time of collation, a principal rejection rate indicating a probability that a principal is rejected at the time of collation, and an equal error rate, which is a probability that the stranger acceptance rate and the principal rejection rate are equal, becomes substantially constant regardless of a registration condition and/or a collation condition, and a determination unit that determines whether the collation object person is the registrant by comparing the adjusted score and a predetermined threshold.