Liveness Detection via Sub-Surface Scattering Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current liveness detection methods in face recognition systems are inadequate as they rely on specific hardware and require user cooperation, failing to effectively differentiate between a living person and attacks like 3D face models or masks, and impacting user experience and efficiency.
Innovation Solution
A liveness detection method using a static structured light source to determine sub-surface scattering intensity on a face, which reduces user cooperation and improves accuracy and usability by employing a ratio of gradient magnitudes to total brightness within a predetermined region, and optionally using Fourier transforms on sub-image regions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional liveness detection techniques are used, then liveness detection can be performed, but it requires specific hardware devices and complex active light sources, increasing device complexity
Solution Approach 1:
The patent extracts the essential liveness detection function from complex hardware systems and implements it using a simple static structured light source. By removing the dependency on infrared cameras, depth cameras, and active light sources, the solution achieves liveness detection with minimal hardware requirements while maintaining effectiveness against attacks from static pictures, 3D face models, and masks.
Solution Approach 2:
The patent replaces expensive and complex hardware devices with a simple, inexpensive static structured light source. This disposable-like approach uses basic lighting components that can be easily implemented without requiring specialized equipment, thereby reducing device complexity while maintaining detection reliability.
2Reliability
If conventional liveness detection systems are used, then liveness detection can be performed, but it requires user cooperation and instruction following, reducing ease of operation
Solution Approach 1:
The patent implements self-service liveness detection where the system automatically captures facial images and analyzes sub-surface scattering characteristics without requiring the user to perform any actions or follow instructions. The system autonomously determines liveness status by capturing images under static structured light and computing detection parameters, thereby eliminating user cooperation requirements while maintaining detection accuracy.
Solution Approach 2:
The patent performs preliminary actions by pre-configuring the structured light source and detection parameters before actual liveness detection. The system is prepared in advance with the necessary hardware setup and software algorithms, allowing it to immediately perform accurate liveness detection without requiring users to cooperate during the detection process.
3Reliability
If conventional liveness detection methods are used, then simple attacks from static pictures can be prevented, but they cannot effectively differentiate between living persons and 3D face models or masks
Solution Approach 1:
The patent changes the detection parameter from simple image matching to sub-surface scattering intensity measurement. By calculating the ratio of gradient magnitudes to total brightness and analyzing scattering characteristics under static structured light, the system achieves high precision differentiation between living persons and attackers using 3D face models or masks, while maintaining effectiveness against static picture attacks.
Solution Approach 2:
The patent applies local quality analysis by examining specific regions of the face image where sub-surface scattering occurs. The system calculates detection parameters for predetermined regions based on gradient magnitudes and brightness values, allowing it to detect the unique scattering characteristics of living skin versus artificial materials with high precision, thereby effectively differentiating between legitimate users and attackers.
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
Effectively differentiates between a living body and non-living entities like masks or 3D face models, enhancing the accuracy and user experience of face recognition systems by utilizing a static structured light source for sub-surface scattering analysis.
Implementation Method 1
irradiating an object to be detected with structured light; obtaining first facial image data of the object to be detected under irradiation of the structured light
Implementation Method 2
determining, based on the first facial image data, a detection parameter that indicates a sub-surface scattering intensity of the structured light on a face of the object to be detected
Data Source
AI summary
The application provides a liveness detection method capable of implementing liveness detection, and a liveness detection system that employs the liveness detection method. The liveness detection method comprises: irradiating an object to be detected with structured light; obtaining first facial image data of the object to be detected under irradiation of the structured light; determining, based on the first facial image data, a detection parameter that indicates a sub-surface scattering intensity of the structured light on a face of the object to be detected; and determining, based on the detection parameter and a predetermined parameter threshold, whether the object to be detected is a living body.