Remote Face Access Authentication Using Periodic Light Fraud Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing biometric authentication methods for remote access are vulnerable to frauds such as injection and presentation attacks, particularly inconvenient for users with disabilities, and lack robustness against fraud without user discomfort.
Innovation Solution
A method using a terminal with a light source and camera that controls a time-variable, periodic light signal to acquire a time-domain video signal, estimating the contribution of the emitted signal, calculating a signal-to-noise ratio to detect fraud by injection or presentation, and authorize access based on the ratio, without requiring specific synchronization or image-by-image analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a camera remotely acquires an image of the user's face for biometric authentication, then remote access is enabled, but the system becomes vulnerable to injection and presentation frauds
Solution Approach 1:
The patent applies periodic action by controlling the light source to emit a time-variable, periodic signal during image acquisition. This periodic modulation allows the system to detect fraud by analyzing the temporal characteristics of the reflected light, distinguishing real faces from fraudulent presentations through the consistent periodic response of genuine facial features.
Solution Approach 2:
The patent implements parameter changes by varying the temporal parameters of the light source (emitting periodic signals with specific frequencies and durations) and analyzing corresponding parameters in the acquired images. By changing the temporal illumination pattern and measuring the reflected light's temporal characteristics, the system gains additional dimensions for fraud detection beyond static image analysis.
2Reliability
If random gestures are required for authentication to detect fraud, then fraud detection capability is improved, but user convenience deteriorates especially for users with disabilities
Solution Approach 1:
The patent applies self-service by making the fraud detection process automatic and passive. The system automatically controls the light source, captures images, and analyzes temporal patterns without requiring any active participation or specific gestures from the user. The user simply needs to present their face, and the system handles all fraud detection operations autonomously, making it accessible to users with various disabilities.
3Measurement precision
If image-by-image analysis is performed to detect fraud, then detection accuracy is improved, but computational complexity and memory requirements increase
Solution Approach 1:
The patent applies extraction by isolating and analyzing only the temporal characteristics of the light reflection from facial features. Instead of performing comprehensive image-by-image analysis, the system extracts the specific temporal signal components that result from the periodic illumination, focusing computational resources on the most discriminative features for fraud detection while ignoring redundant spatial and temporal information.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The method provides robust fraud detection against screen fraud and printed photos, is accessible to all users, and reduces computational and memory intensity, ensuring secure remote access without user inconvenience.
Implementation Method 1
acquisition of a time-domain video signal by the camera
Implementation Method 2
control, during the acquisition stage, of the light source according to a time-variable, periodic signal
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
The present invention relates to a method for securing remote access to data from a user terminal (1) comprising a light source (5) and a camera (3), by: - acquiring a time-domain video signal by the camera (3); - controlling the light source (5) according to an imposed time-variable emitted signal, at least one parameter of which is time-invariant and of randomly fixed value; - evaluating, from images of the acquired time-domain signal, fraud by: - estimating a contribution of the imposed emitted signal to the acquired time-domain video signal as a function of said parameter; - evaluating a noise level of the acquired time-domain video signal; - calculating a signal-to-noise ratio by dividing the contribution by the noise level; - authorizing continued access to the data source as a function of the calculated signal-to-noise ratio.