Multi-Gate Face Verification Using Lane-Aware Image Regions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In walkthrough face authentication systems with multiple adjacent gates, there is a risk of erroneous recognition of individuals due to overlapping images from adjacent lanes, leading to incorrect identification of persons passing through the wrong gate.
Innovation Solution
A face authentication system that uses imaging devices installed near each gate to capture and process images, employing a target extraction unit to identify the center and end areas within the captured image, a target determination unit to determine if a person is moving towards the correct gate, and a collation unit to perform face authentication only on those in the center area, excluding those in the end area from the collation process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a single camera is installed at each gate to capture images of persons approaching, then the system structure is simple and easy to operate, but persons from adjacent lanes are erroneously recognized as moving toward the correct gate
Solution Approach 1:
The patent divides the captured image into multiple areas (first area, second area, third area) corresponding to different lanes. By segmenting the image space, the system can distinguish between persons in the correct lane and persons from adjacent lanes, preventing erroneous recognition while maintaining the simple single-camera structure at each gate.
Solution Approach 2:
The patent applies different processing rules to different areas of the captured image. Persons in the first area (correct lane) are subjected to full authentication, while persons in the second and third areas (adjacent lanes) are excluded from authentication. This local differentiation resolves the contradiction by maintaining system simplicity while improving identification accuracy through spatial awareness.
2Productivity
If collation is performed on all detected persons without lane distinction, then the authentication process is comprehensive, but erroneous recognition of persons from adjacent lanes occurs
Solution Approach 1:
The patent extracts and removes persons from adjacent lanes (second and third areas) from the authentication process. By taking out these erroneously detected persons, the system maintains comprehensive authentication for valid persons while eliminating erroneous recognition, thus preserving productivity without sacrificing reliability.
Solution Approach 2:
Instead of performing authentication on all detected persons (excessive action), the patent applies authentication only to persons in the correct lane (first area). This partial action approach ensures that authentication is performed comprehensively on valid targets while avoiding wasted processing on erroneous detections, optimizing both productivity and reliability.
3Adaptability or versatility
If the camera captures a wide area to ensure all approaching persons are detected, then detection coverage is complete, but persons from adjacent lanes are included in the captured image causing recognition errors
Solution Approach 1:
The patent segments the detection area into multiple zones (first, second, and third areas) corresponding to different lanes. This segmentation allows the camera to maintain wide detection coverage while the processing system distinguishes between persons in the correct lane versus adjacent lanes, resolving the contradiction between adaptability and reliability.
Solution Approach 2:
The patent introduces an intermediary processing layer that analyzes the spatial position of detected persons within the captured image. This intermediary step filters out persons from adjacent lanes while preserving persons from the correct lane, enabling the system to maintain wide detection coverage without compromising identification accuracy.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A collation system of the present invention includes imaging means for acquiring a captured image of a pre-passage side area with respect to each of gates arranged in parallel with each other, and collation means for performing a collation process on the captured image of the pre-passage side area for each of the gates, between a previously registered target and a target included in the captured image. The collation means performs the collation process on the basis of a target in the captured image corresponding to one of the gates and a target in the captured image corresponding to another one of the gates.