Liveliness Detection via Dual Illumination Biometric Spoofing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing biometric identification systems using mobile devices struggle to distinguish between images of living body parts and spoofs, such as images held in front of the camera, which can lead to unauthorized access to sensitive information.
Innovation Solution
A computer-implemented method that uses a device with an illumination source to take two images of a scene potentially containing a living body part with biometric characteristics: one image without illumination and one with illumination. These images are then processed by a neural network to compare and determine if they are from a living body part, thereby deciding whether to perform an identification algorithm.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a single image is used for biometric identification, then the identification process is simple and fast, but the system is vulnerable to spoofing attacks using images of body parts
Solution Approach 1:
The imaging process is segmented into multiple captures: at least two images are taken with different illumination conditions (one with illumination source activated, one without). This segmentation allows the system to analyze differential reflections and detect spoofing attempts by comparing how different materials (real skin vs. printed image) reflect light under varying illumination conditions.
Solution Approach 2:
The illumination parameter is changed between image captures by activating and deactivating the illumination source. This parameter change creates different reflection patterns that reveal the true nature of the subject (real body part vs. spoof), enabling the system to distinguish between genuine biometric data and fraudulent copies.
2Reliability
If multiple images with different illumination are captured, then spoofing detection accuracy is improved, but the identification process time increases
Solution Approach 1:
The system performs preliminary liveliness detection by comparing illumination differences before proceeding to full biometric identification. If the preliminary check fails (indicating a spoof), the time-consuming identification algorithm is never executed. This preliminary action filters out fraudulent attempts early, saving time for genuine users while maintaining security.
Solution Approach 2:
The system performs a partial analysis (comparing only illumination differences) as a quick preliminary check before committing to the full identification process. This partial action is sufficient to detect spoofs and avoid unnecessary processing time, while still allowing genuine users to proceed to complete identification.
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
The method effectively differentiates between images of living body parts and spoofs by analyzing the differences in light reflection characteristics, enhancing the reliability of biometric identification and preventing unauthorized access.
Implementation Method 1
a device with an illumination source that, when activated, emits visible light
Implementation Method 2
analyzing the differences in light reflection characteristics
Data Source
AI summary
A computer-implemented method for identifying a user uses a computing device comprising an illumination source that, when activated, emits visible light, the method comprising taking two images of a scene potentially comprising a living body part carrying a biometric characteristic, wherein a first image is taken without the illumination source activated and the second image is taken with the illumination source activated, transferring the first image and the second image to a neural network and processing, by the neural network the first image and the second image, by comparing the first image and the second image, thereby determining whether the first image and the second image are of the living body part, and, if it is determined that the first image and the second image are of the living body part, performing an identification algorithm to find a biometric characteristic for identifying the user.