Liveness Detection via Angular Signal Similarity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current liveness detection methods fail to effectively distinguish between live users and spoofing attempts, particularly with high-definition video playback, leading to unreliable biometric authentication results.
Innovation Solution
A method and system that calculate angles between the terminal device and the user's face in a video, generating signals and a similarity score to determine user liveliness, with a threshold score to verify the user's physical presence and identity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If traditional liveness detection methods (motion-based or eye blink detection) are used, then implementation simplicity is maintained, but detection accuracy against high-definition video playback spoofing deteriorates
Solution Approach 1:
The patent transitions from analyzing single-frame or simple temporal sequences to analyzing multi-dimensional angular relationships. By calculating angles between the terminal device, face features, and vertical axes across multiple frames, the system creates a richer dimensional space for detection that can distinguish real head movements from video playback
Solution Approach 2:
The system dynamically calculates angles for each frame in the video sequence and analyzes the temporal patterns of these angular changes. This dynamic approach captures the natural dynamics of human head movement versus the rigid or unnatural dynamics of video playback, improving detection accuracy without requiring overly complex static analysis
2Manufacturing precision
If high-definition video playback is used for spoofing, then the quality of fraudulent biometric data improves, but the ability to detect spoofing attempts deteriorates
Solution Approach 1:
The system provides feedback by comparing the calculated angular signals against expected patterns of natural head movement. The similarity score between first and second signals serves as a feedback mechanism that indicates whether the video represents a live user or a spoofing attempt, allowing the system to reject high-definition video playback when angular patterns don't match natural movement
Solution Approach 2:
The patent introduces angular calculations as an intermediary layer between the raw video data and the liveness detection decision. By computing angles between the terminal device, face features, and vertical axes, the system creates an intermediate representation that reveals subtle differences between real and spoofed videos, even when the spoofing video is high-definition
Data Source
AI summary
A method for enhancing user liveness detection is provided that includes calculating, by a computing device, a first angle and a second angle for each frame in a video of captured face biometric data. The first angle is between a plane defined by a front face of the terminal device and a vertical axis, and the second angle is between the plane defined by the front face of the terminal device and a plane defined by the face of the user. Moreover, the method includes creating a first signal from the first angles and a second signal from the second angles, calculating a similarity score between the first and second signals, and determining the user is live when the similarity score is at least equal to a threshold score.