Rolling Shutter Biometric Authentication via Synchronized Illumination Sequences
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Biometric authentication systems face challenges in distinguishing between live subjects and spoof materials, such as silicon, plastic, or paper, due to the lack of effective methods for real-time identification of hardware and biometric presentation attacks, particularly in systems using rolling shutter image capture modes.
Innovation Solution
Implementing a biometric authentication system that uses a rolling shutter mode in conjunction with an illumination sequence pattern, where the frequency of illumination from one or more sources is varied and synchronized with the shutter, allowing for the verification of pixel values corresponding to specific wavelengths, thereby differentiating between live and spoof materials by analyzing the illumination sequence patterns in captured images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a rolling shutter mode is used for image capture, then the system can operate with standard hardware, but the system cannot distinguish between live subjects and spoof materials
Solution Approach 1:
The illumination source emits light in periodic pulses at specific wavelengths that are synchronized with the rolling shutter exposure cycles. This periodic illumination creates distinct temporal patterns in the captured image data that allow differentiation between live subjects and spoof materials without requiring complex additional hardware
Solution Approach 2:
The system changes the temporal and spectral parameters of illumination by using pulsed light at specific wavelengths that correspond to the rolling shutter exposure timing. This parameter modulation creates unique signatures in the pixel data that reveal whether the subject is live or spoofed
2Reliability
If additional hardware is added for spoof detection, then authentication security is improved, but system cost and complexity increase
Solution Approach 1:
The existing rolling shutter camera and illumination source are made to serve dual purposes: standard imaging and spoof detection. By synchronizing the illumination pulses with the rolling shutter timing, the system extracts authentication information from the same hardware components used for normal operation, eliminating the need for separate detection hardware
Solution Approach 2:
The illumination source and camera are designed to perform multiple functions: providing visibility for the subject and simultaneously encoding authentication information through synchronized pulsed illumination. This multi-functionality allows spoof detection without adding dedicated hardware 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 enables real-time identification of hardware and biometric presentation attacks, reduces the need for additional hardware, and enhances security by preventing unauthorized access through spoof detection, while maintaining cost-effectiveness for the underlying biometric authentication system.
Implementation Method 1
a first set of pixel values of the first image corresponds to illumination of a first representative wavelength, and at least a second set of pixel values of the first image corresponds to illumination of a second representative wavelength
Implementation Method 2
data corresponding to a first image captured using an image sensor
Data Source
AI summary
Technology described herein includes a method that includes receiving, at one or more processing devices, data corresponding to a first image, and determining, by the one or more processing devices based on the received data, that a first set of pixel values of the first image corresponds to illumination of a first representative wavelength, and at least a second set of pixel values of the first image corresponds to illumination of a second representative wavelength. The illuminations of the first and second representative wavelengths constitute at least a portion of a first illumination sequence pattern used in capturing the first image. The method also includes determining that the first illumination sequence pattern matches a second illumination sequence pattern associated with a device from which the first image is expected to be received, and in response, initiating a biometric authentication process for authenticating a subject represented in the first image.