Fingerprint Sensor Damaged Pixel Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The integration of a learning function in fingerprint identification sensors that adds pixel features of damaged units into templates increases the False Accept Rate (FAR), potentially leading to security hazards in mobile terminals.

Innovation Solution

A method and device that detect the number of damaged pixel units in a fingerprint identification sensor and stop matching identification when the number reaches a preset threshold, preventing the inclusion of damaged pixel features into the template and thereby reducing the FAR.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a learning function is added to reduce False Reject Rate by incorporating pixel features into fingerprint templates, then identification accuracy improves, but damaged pixel features are included in templates causing False Accept Rate to increase

Engineering Contradiction:
ImproveFalse Reject RateVSAvoidFalse Accept Rate
Core Design Contradiction:
ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The patent performs preliminary detection of damaged pixel units before fingerprint template generation. By identifying and excluding damaged pixels in advance, the system prevents their features from being incorporated into the template, thus avoiding the increase in False Accept Rate while still benefiting from the learning function to reduce False Reject Rate

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent extracts and removes damaged pixel units from the fingerprint image data before template processing. By separating and eliminating the harmful damaged pixel features, the system ensures that only valid fingerprint features are used for template generation, resolving the contradiction between improving identification accuracy and preventing false accepts

Inventive Principle:
Principle #2Taking out (Extraction)

2Productivity

If damaged pixel features are included in fingerprint templates through learning function, then fewer pixels are needed for identification, but security is compromised due to increased False Accept Rate

Engineering Contradiction:
ImproveIdentification efficiencyVSAvoidSecurity
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The system performs preliminary detection and exclusion of damaged pixel units before template generation. This ensures that only valid pixel features are used for identification, maintaining both identification efficiency and security by preventing damaged pixels from compromising the template's reliability

Inventive Principle:
Principle #10Preliminary action

3Ease of operation

If the number of damaged pixel units is not monitored, then fingerprint identification can proceed normally, but security hazards arise when damaged pixel features are inadvertently used

Engineering Contradiction:
ImproveIdentification operationVSAvoidSecurity
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent implements a feedback mechanism that continuously monitors the fingerprint image for damaged pixel units and adjusts the template generation process accordingly. When damaged pixels are detected, the system provides feedback to exclude them from the template, ensuring that identification operations remain easy while maintaining security through active monitoring and adjustment

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP3188078B1Method and device for fingerprint identification
Publication Date: 2021.07.14 XIAOMI INC
  • EP3188078B1 patent drawingFigure 1~2
  • EP3188078B1 patent drawingFigure 3A
  • EP3188078B1 patent drawingFigure 3B

AI summary

The present disclosure discloses a method and device for fingerprint identification, and relates to fingerprint identification. The method for fingerprint identification includes that: it is detected (201) whether the number of damaged pixel units in a fingerprint identification sensor reaches a preset threshold value or not, the damaged pixel units referring to physically damaged pixel units in the fingerprint identification sensor; and if the number of the damaged pixel units reaches the preset threshold value, matching identification of a fingerprint image acquired by the fingerprint identification sensor is stopped (202).