Spoof Detection via Specular and Diffuse Reflections
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Optical fingerprint sensors are vulnerable to spoofing, as they can be easily deceived by two-dimensional representations, lacking effective methods to distinguish between genuine and fake biometric inputs.
Innovation Solution
The method employs a controllable light source with varying intensity and color patterns to capture images under both specular and diffuse illumination, using metrics extracted from these images to differentiate between live fingers and spoofs through machine learning algorithms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If optical fingerprint sensors use simple illumination, then device complexity is reduced, but spoof detection capability deteriorates
Solution Approach 1:
The illumination system is segmented into multiple controllable light source units that can be independently activated. The sensor captures images under different illumination conditions (specular and diffuse) by selectively activating different light source units, enabling spoof detection without requiring a single complex illumination system.
Solution Approach 2:
The patent adds the dimension of illumination variation by capturing images under different lighting conditions (specular vs diffuse illumination). This dimensional approach allows the system to detect spoofs by analyzing differences in reflection properties without increasing physical device complexity.
2Measurement precision
If the system captures images under multiple illumination conditions, then spoof detection accuracy is improved, but image acquisition time increases
Solution Approach 1:
The light source units are activated in periodic sequences, with different units turned on and off in a predetermined pattern. This allows the sensor to capture multiple illumination conditions in rapid succession, improving spoof detection accuracy while minimizing the time penalty through efficient temporal multiplexing.
Solution Approach 2:
The system uses a predetermined activation pattern for light source units that is established in advance. This preliminary configuration allows the sensor to efficiently capture necessary illumination variations without real-time decision-making, reducing image acquisition time while maintaining detection accuracy.
3Area of stationary object
If multiple light source units are used for illumination, then illumination coverage is improved, but device complexity increases
Solution Approach 1:
Multiple light source units serve universal functions: they can be individually activated to provide specular illumination, diffuse illumination, or combined illumination depending on the detection needs. This multi-functionality allows comprehensive illumination coverage while maintaining relatively simple device architecture through shared components.
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
This approach significantly enhances the reliability of biometric authentication by accurately distinguishing between live fingers and spoofs, improving the security of optical fingerprint sensors.
Implementation Method 1
an image sensor comprising a photodetector pixel array configured to capture an image of the object
Implementation Method 2
a controllable light source comprising light source units
Data Source
AI summary
The present invention relates biometric authentication using an optical biometric arrangement comprising an image sensor comprising a photodetector pixel array configured to capture an image of an object, the image sensor being arranged under a controllable light source comprising light source units, the method comprising: providing a light pattern comprising portions of different light intensity for illuminating the object; acquiring an image of the object, the image comprising image portions corresponding to the portions of different light intensity of the light pattern illuminating the object, at least one image portion being captured by pixels in he photodetector pixel array arranged directly under a light source unit being active during image acquisition, and at least one image portion being captured by pixels in the photodetector pixel array arranged under an at least partly in-active illumination area of the controllable light source during image acquisition, performing biometric authentication at least partly based on metrics extracted from the image portions.