Fingerprint Feature Extraction via Impairment Data Suppression

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Fingerprint sensors face challenges in accurately extracting feature data due to quasi-stationary noise, such as capacitive noise, caused by material imperfections and sensor impairments, which can lead to false positives and unauthorized access.

Innovation Solution

A method and system that capture and store images of impairment data, allowing the processing unit to reduce reliance on feature data from sections with impairment, using confidence and presence metrics to suppress or exclude noise, thereby enhancing the accuracy of fingerprint feature extraction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If sub-μm precision and extremely pure materials are used to eliminate capacitive noise, then measurement precision is improved, but device complexity and manufacturing difficulty increase

Engineering Contradiction:

Improvefingerprint feature extraction accuracyVSAvoidmaterial precision requirements

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs preliminary capture of impairment data during sensor manufacturing or initial operation, storing it for later use. This preliminary action allows the system to pre-identify and catalog noise patterns before they interfere with actual fingerprint measurements, eliminating the need for ultra-precise materials during operation.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary impairment data map that mediates between the raw sensor output and the final fingerprint analysis. This intermediary layer identifies and flags noisy regions, allowing the system to work with standard materials while compensating for imperfections through software-based noise characterization and exclusion.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If impairment data is completely excluded from fingerprint analysis, then reliability is improved, but loss of information increases

Engineering Contradiction:

Improveauthentication accuracyVSAvoidfingerprint feature data

Core Design Contradiction:

ReliabilityVSLoss of information

Solution Approach 1:

The system applies local quality control by selectively excluding only those specific regions or features that are contaminated by noise, while preserving and analyzing all other clean fingerprint data. This localized approach maintains high reliability by excluding problematic areas while retaining maximum useful information from the fingerprint image.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The impairment data map serves as feedback information that guides the fingerprint analysis process. By continuously referencing the stored impairment characteristics, the system can dynamically adjust which features to trust and which to exclude, optimizing the balance between reliability and information retention based on the specific noise patterns present.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11170196B2Extracting fingerprint feature data from a fingerprint image

Publication Date: 2021.11.09 FINGERPRINT CARDS IP AB

AI summary

The invention relates to a method of a fingerprint sensing system of extracting fingerprint feature data from an image captured by a fingerprint sensor of the fingerprint sensing system, and a fingerprint sensing system performing the method.