Liveness Detection Using Dual Illumination Feature Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current liveness detection methods for biometric authentication are inadequate in distinguishing live users from spoofing attempts, such as 2D images and physical models, leading to low confidence and accuracy in remote authentication transactions.
Innovation Solution
A method and system that select first and second images captured under different illumination conditions, calculate feature values and vectors, and determine user liveness by computing a confidence score that meets or exceeds a threshold, using feature calculation windows and a computing device with a processor and memory to process biometric data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional liveness detection methods (motion analysis, eye blink detection, pattern illumination) are used, then the system can detect some spoofing attempts, but the accuracy and confidence in distinguishing live users from sophisticated spoofing attacks (such as 2D images and physical models) remains low
Solution Approach 1:
The patent changes the parameter being measured from simple motion or illumination response to subsurface scattering properties of skin tissue. By analyzing how light scatters beneath the skin surface rather than just surface-level characteristics, the system achieves higher accuracy in distinguishing live users from spoofing attempts while maintaining reliability.
Solution Approach 2:
The patent introduces an intermediary analysis layer that processes captured images through specific algorithms to extract subsurface scattering characteristics. This intermediary processing transforms ordinary image data into meaningful liveness indicators, enabling accurate detection of sophisticated spoofing attempts that evade traditional methods.
2Measurement precision
If sophisticated liveness detection algorithms are implemented to improve accuracy, then the system can better distinguish live users from spoofing attempts, but the computational complexity and processing requirements increase
Solution Approach 1:
The patent extracts only the critical subsurface scattering characteristics from the captured images rather than performing comprehensive analysis of all image features. By focusing specifically on the subsurface light scattering properties and ignoring irrelevant surface details, the system achieves high accuracy with reduced computational complexity.
Solution Approach 2:
The patent segments the image analysis process into distinct stages: capturing images under controlled illumination, extracting subsurface scattering features from specific regions, and comparing these features against stored biometric data. This segmentation allows complex analysis to be broken into manageable steps that reduce overall computational burden.
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
Enhances the accuracy and trustworthiness of liveness detection, reducing false positives and improving the reliability of biometric authentication transactions by effectively distinguishing between live users and spoofing attempts.
Implementation Method 1
selecting first and second images from a sequence of images captured under different illumination conditions
Data Source
Figure 1~2
Figure 3~5
Figure 6~10
AI summary
A method for detecting user liveness is provided that includes selecting first and second images from a sequence of images. The first and second images are captured under different illumination conditions. The method further includes locating feature calculation windows in corresponding positions on the first and second images. Each window includes a first area and a second area. Moreover, the method includes calculating, by a computing device, a feature value for each window position based on pixels, within the windows located at the position, from the first and second images. Furthermore, the method includes calculating a feature vector from the feature values, calculating a confidence score from the feature vector, and determining the sequence of images includes images of a live user when the confidence score is equal to or greater than the threshold score.