Fingerprint Sensor Impairment Data Comparison for Spoofing Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Fingerprint sensing systems face challenges in authenticating users due to impairment data, such as quasi-stationary noise, which can be manipulated by malicious third parties, leading to false positives and unauthorized access.
Innovation Solution
A method that captures and stores impairment data from the fingerprint sensor, extracts fingerprint feature data and impairment feature data, and compares them to determine if the authentication should be terminated, thereby preventing false positives by identifying manipulated background images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a calibration image is used to compensate for fixed pattern noise in the fingerprint sensor, then the measurement precision is improved, but the reliability deteriorates because a malicious third party may manipulate the stored calibration image to spoof the fingerprint system
Solution Approach 1:
The patent introduces an intermediary verification process that compares impairment features in the captured fingerprint image with impairment features in the stored calibration image. This intermediary comparison mechanism acts as a mediator to detect manipulations without compromising the noise compensation benefit, thereby resolving the contradiction between measurement precision and reliability
Solution Approach 2:
The system implements feedback by comparing impairment data from the captured image with impairment data from the calibration image, and using this comparison result to determine whether to proceed with authentication. This feedback loop enables the system to detect spoofing attempts while maintaining the noise compensation functionality
2Measurement precision
If sub-μm precision and extremely pure materials are used to eliminate capacitive noise, then the measurement precision is improved, but the device complexity and manufacturing difficulty increase
Solution Approach 1:
The patent creates a digital copy of the impairment pattern through the calibration image, which is then used to compensate for noise in subsequent fingerprint images. This copying approach eliminates the need for physical modifications to the sensor materials, thereby resolving the contradiction between measurement precision and device complexity
Solution Approach 2:
The system changes the approach from modifying physical parameters (material purity, thickness precision) to modifying data parameters (calibration image, impairment compensation). This parameter transformation allows noise elimination without requiring sub-μm precision materials or complex manufacturing processes
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 prevents false positives by identifying manipulated background images and ensuring accurate user authentication, even in the presence of impairment data, by suppressing impairment data and updating the background image to account for changing sensor conditions.
Implementation Method 1
For capacitive sensors, when the user touches a fingerprint sensing area (covered by e.g. glass or ceramic) of the smart phone, a capacitor is formed between a surface of the fingerprint sensing area and the fingerprint sensor arranged inside the smart phone. By measuring the capacitance between the surface touched by the user and the sensor at each pixel, the fingerprint of the user may be derived
Data Source
AI summary
The invention relates to a fingerprint sensing system and a method of the fingerprint sensing system of enabling authentication of a user based on fingerprint data captured by a fingerprint sensor of the fingerprint sensing system. The method comprises capturing at least one image of a fingerprint of a user's finger contacting the fingerprint sensor, acquiring a stored image comprising impairment data caused by impairments that the fingerprint sensor is subjected to, extracting fingerprint feature data from the captured at least one image, extracting impairment feature data from the acquired image, and comparing at least a subset of the extracted fingerprint feature data to at least a subset of the extracted impairment feature data of the acquired image, and if there is a match the user is not authenticated.