Liveness Detection via Face-Background Motion Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Authentication systems based on facial recognition struggle to differentiate between a live human and an image of a human, leading to potential unauthorized access when an image of an authorized user is used to spoof the system.
Innovation Solution
A liveness detection system that receives a video stream from an image capture device, determines motion between the face and background, and prompts the user for specific actions to differentiate between a live user and an image by analyzing motion and facial expressions, using a processor to determine if the face corresponds to an actual, live user or an image.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If facial recognition is used for authentication, then authentication speed and convenience are improved, but security against spoofing attacks deteriorates
Solution Approach 1:
The system transitions from static image-based facial recognition to dynamic video-based liveness detection. By analyzing temporal changes in facial features across multiple video frames, the system can detect genuine facial movements (muscle contractions, blood flow changes) that distinguish live faces from static images or video replays, thereby maintaining authentication speed while significantly improving spoofing resistance
Solution Approach 2:
The system performs preliminary liveness detection analysis during the authentication process by examining facial region dynamics before final authentication decisions. Motion detection algorithms continuously monitor the facial area for characteristic live human movements, and only after confirming liveness does the system proceed with facial recognition matching, thus preventing spoofing attempts at an early stage
2Measurement precision
If motion detection of facial features is implemented, then liveness detection accuracy is improved, but system complexity increases
Solution Approach 1:
The system divides the facial region into multiple sub-regions (eyes, nose, mouth, cheeks) and independently analyzes motion characteristics in each segment. This segmentation allows the system to detect subtle facial muscle movements and blood flow patterns in specific areas without requiring complex global analysis, thereby improving liveness detection accuracy while keeping computational complexity manageable through localized processing
Solution Approach 2:
The system replaces complex mechanical or hardware-based liveness detection mechanisms with software-based computer vision algorithms. By using image processing techniques to analyze pixel-level changes in the facial region across video frames, the system achieves high liveness detection accuracy without requiring additional physical sensors or complex hardware modifications, thus reducing overall system complexity
Data Source
AI summary
A liveness detection method comprising: receiving plural pictures of a video stream comprising a face and an adjacent background; determining motion of the face and the background, the motion determined over the plural pictures; comparing the motion between the face and the background; and determining whether the face corresponds to an actual, live user or an image of the user based on the comparison, the determinations performed by a processor.