Continuous Authentication Image Area Control for Multi-Person Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In continuous authentication systems, there is a risk that when multiple users check in, people other than the target person may appear in the captured image, leading to inaccurate detection of the target person's appearance features.
Innovation Solution
A control method that includes controlling the target detection area by narrowing it when multiple people are detected in the image, ensuring the target person is facing a predetermined direction, and extracting feature information only from this area.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the camera captures the appearance of the authenticated person, then the authentication process can be completed, but when multiple people are present, the detection accuracy of the target person deteriorates
Solution Approach 1:
The patent divides the detection area into multiple regions and identifies the specific region where the authenticated person is located. By segmenting the image processing task and focusing only on the relevant region, the system maintains authentication reliability while improving detection accuracy among multiple people.
Solution Approach 2:
The patent introduces an intermediary step of determining the detection area based on authentication information before extracting appearance features. This intermediary region identification acts as a mediator that filters out other people from the detection process, ensuring accurate target person detection while maintaining authentication reliability.
2Quantity of substance
If the detection area is widened to capture more context, then more information can be acquired, but the detection accuracy of the target person decreases
Solution Approach 1:
The patent applies local quality by focusing the detection and feature extraction process on a specific local region (the detection area) rather than the entire image. This localized approach ensures high detection accuracy for the target person while still acquiring necessary contextual information within that region.
Solution Approach 2:
The patent extracts only the necessary information from the detection area where the authenticated person is located. By taking out and processing only the relevant portion of the image, the system maintains detection accuracy while acquiring sufficient information for authentication purposes.
Data Source
Figure 1
Figure 2(a)~2(b)
Figure 3
AI summary
In a control method, a computer executes a process including, when a plurality of people are detected from an image including a person to be authenticated who has been successfully authenticated using identification information, controlling a target detection area for detecting the person in the image.