Eye Gaze Angle Tracking for Biometric Liveness Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing liveness detection systems are vulnerable to photo and video spoofing attacks, which compromise security in biometric authentication systems.
Innovation Solution
An information processing system that utilizes eye gaze detection through a processor to calculate moving averages and patterns of gaze angles, determining liveness by correlating eye gaze movements with displayed objects on a screen, employing AI and machine learning with custom-trained Deep Neural Networks to enhance spoof detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional liveness detection techniques are used, then basic authentication can be performed, but the system becomes vulnerable to photo and video spoofing attacks
Solution Approach 1:
The system transitions from static image analysis to dynamic video analysis by capturing multiple frames and tracking gaze angle changes over time. The processor calculates gaze angles for each frame and analyzes temporal patterns, making the detection system dynamic and adaptive to real-time eye movements, thereby preventing spoofing attacks using static photos or pre-recorded videos.
Solution Approach 2:
The system implements feedback by continuously monitoring gaze angle sequences and comparing them against expected patterns. The processor analyzes the temporal consistency of gaze movements and provides feedback determination on liveness based on whether the observed patterns match natural human eye movement characteristics, enabling reliable detection of spoofing attempts.
2Object-affected harmful factors
If photo and video spoofing attacks are prevented through advanced detection, then security is enhanced, but the complexity of the detection system increases
Solution Approach 1:
The system segments the liveness detection process into distinct analytical components: gaze angle extraction from individual frames, temporal pattern analysis across frame sequences, and final liveness determination. This segmentation allows each component to be optimized independently while maintaining overall system manageability and reducing implementation complexity.
Solution Approach 2:
The processor performs multiple functions using the same hardware resources: it extracts gaze angles, analyzes temporal patterns, and determines liveness all within a unified processing pipeline. This multi-functionality approach avoids the need for separate dedicated hardware for each detection function, thereby enhancing security while controlling system complexity.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An apparatus includes: a memory storing one or more instructions; and a processor configured to execute the one or more instructions to: obtain a plurality of images, each of the plurality of images including an eye of a subject; obtain a plurality of gaze angles, each of the plurality of gaze angles corresponding to the eye of the user; and detect liveness of the subject based on the plurality of gaze angles.