Face Recognition Liveness Detection Using User-Specific Eye Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing face recognition systems struggle to accurately determine whether a person in an image is a living subject, particularly when using general-purpose threshold values for eye opening/closing detection, which can lead to inaccurate determinations due to variations in physical features among individuals.
Innovation Solution
An information processing apparatus that sets user-specific threshold values for eye opening/closing detection based on biometric determination parameters, determined through the analysis of individual eye motion patterns, to enhance the accuracy of distinguishing between living subjects and photographs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If general-purpose threshold values are used for eye opening/closing detection, then the system is simple to operate, but the measurement precision deteriorates due to variations in physical features among individuals
Solution Approach 1:
The system performs preliminary learning of eye opening/closing patterns during a registration phase before actual authentication. The biometric determination parameter is calculated in advance based on the registered user's eye motion characteristics, so that during authentication, the pre-calculated parameter can be directly applied without real-time complex calculations
Solution Approach 2:
The system changes the threshold parameter from a fixed general-purpose value to a dynamic user-specific value. The biometric determination parameter is calculated based on individual eye motion patterns (such as the relationship between eye opening degree and closing speed), allowing the detection threshold to adapt to each user's unique physical characteristics
2Reliability
If user-specific threshold values are set based on individual eye motion patterns, then the measurement precision improves, but the device complexity increases due to additional parameter determination steps
Solution Approach 1:
The complex parameter determination is performed in advance during registration, separating the complex calculation phase from the authentication phase. During actual authentication, only simple comparison operations are needed, reducing the perceived complexity while maintaining high reliability
Solution Approach 2:
The system automatically calculates and stores the biometric determination parameter based on the user's own eye motion patterns during registration. The parameter is derived self-service style from the user's natural eye movements without requiring manual intervention or complex user setup
Data Source
AI summary
An information processing apparatus includes a storage device that stores a biometric determination parameter to be used in determination as to whether a person appearing in an image is a living subject, a face recognition unit that performs face recognition, by comparing a face feature amount acquired from a face image of a recognition target and a face feature amount of a registered user, and a determination unit that determines whether the recognition target is a living subject, using the stored biometric determination parameter. The stored biometric determination parameter is determined based on a detection result of an eye opened/closed motion of the registered user. The determination unit determines whether the recognition target is a living subject, by comparing a detection result of a motion including eye opening/closing of the recognition target recognized by the face recognition as the registered user and the stored biometric determination parameter.