Continuous Biometric Authentication Using Normal-Posture Feature Linking

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing biometric authentication methods face challenges in maintaining accurate person identification when users move away from the authentication spot, leading to decreased accuracy due to the use of features extracted in non-normal postures during authentication.

Innovation Solution

The method employs first-type feature information for continuous authentication, using appearance and behavioral features to maintain the authentication state, and second-type feature information for highly accurate identification, leveraging cameras to capture normal postures before and after authentication, and linking this information for continuous tracking.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If feature information is extracted during authentication when the user is in a non-normal posture, then authentication can be performed at the authentication spot, but the accuracy of person identification decreases

Engineering Contradiction:

Improveauthentication capabilityVSAvoidperson identification accuracy

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The system extracts feature information in advance when the user is in a normal posture (before authentication) and stores it for later use during authentication, rather than extracting features during the authentication moment when the user may be in a non-normal posture

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates a copy of the feature information extracted in normal posture and uses this copy during authentication, separating the feature extraction process from the authentication process to avoid posture-related accuracy degradation

Inventive Principle:

Principle #26Copying

2Measurement precision

If feature information is extracted in advance when the user is in a normal posture, then person identification accuracy improves, but the authentication state cannot be maintained when the user moves away from the authentication spot

Engineering Contradiction:

Improveperson identification accuracyVSAvoidcontinuous authentication capability

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The system divides feature information into two types: first-type feature information for continuous authentication (maintaining authentication state) and second-type feature information for high-accuracy identification, allowing each type to serve its specific purpose optimally

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system uses appearance features and behavioral features that can serve dual purposes: maintaining authentication state during movement and providing identification accuracy when needed, making the feature extraction system multi-functional

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentEP4693231A1Determination method, determination program, and information processing device

Publication Date: 2026.02.11 FUJITSU LTD

Figure 1
Figure 2(a)~2(b)
Figure 3

AI summary

In a determination method, a computer executes a process including, extracting first-type feature information of a first person by using a first image captured by a first camera, when second-type feature information is extracted from the first person before or after the first image is captured, identifying a person corresponding to the first person by using the second-type feature information of each of a plurality of people stored in a memory, and when the first-type feature information of a second person is extracted using a second image captured by the first camera or a second camera, identifying a person corresponding to the second person by using the first-type feature information of the first person identified.