Continuous Biometric Authentication Using Normal-Posture Feature Linking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing biometric authentication methods require repeated authentication when a user moves out of the authentication spot, leading to decreased accuracy due to the use of feature information captured in non-normal postures during specific authentication actions.
Innovation Solution
A method that uses first-type feature information for continuous authentication by capturing normal postures before authentication and linking it with second-type feature information for accurate identification, maintaining authentication state through environmental cameras.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If repeated authentication is required when user moves out of authentication spot, then authentication security is maintained, but identification accuracy decreases due to non-normal postures
Solution Approach 1:
The system captures images of the user in normal postures before authentication occurs (preliminary action). These preliminary images serve as reference data for subsequent authentication processes, allowing the system to compare authenticated images against these pre-captured normal posture images, thereby maintaining accuracy even when users are authenticated at different locations and times
2Ease of operation
If feature information captured in specific authentication actions is used, then authentication process is simplified, but identification accuracy decreases due to non-normal postures
Solution Approach 1:
The system extracts and separates the posture assessment function from the authentication flow. Environmental cameras continuously capture user images, and the system extracts posture information independently to determine whether the user is in a normal or non-normal posture. This extracted posture data is then used to selectively apply authentication methods, allowing the simplified authentication process to continue while compensating for posture-related accuracy issues through alternative authentication paths
3Productivity
If environmental cameras are used for continuous authentication, then user tracking is improved, but system complexity increases
Solution Approach 1:
The environmental cameras serve multiple functions: they continuously monitor user presence, capture images for posture analysis, and provide authentication data. By making these cameras multi-functional (universal), the system achieves continuous authentication capability without adding dedicated specialized devices, thereby improving productivity while limiting the increase in system complexity
Data Source
AI summary
A determination method includes, 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.