Fingerprint Template Learning for Dry-Skin Display Authentication

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Fingerprint authentication accuracy in display devices is degraded due to variations in skin state or authentication environment, such as dry skin or bright surroundings.

Innovation Solution

A fingerprint authentication device uses learning techniques to generate pseudo images from enrolled images, improving accuracy by converting low-quality fingerprint images into pseudo images using image conversion models, and adding these to the template for comparison.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If a fingerprint authentication device uses an existing template for authentication, then authentication speed is improved, but the template may be incomplete leading to authentication failures

Engineering Contradiction:
Improveauthentication speedVSAvoidauthentication reliability
Core Design Contradiction:
SpeedVSReliability

Solution Approach 1:

The learning unit generates pseudo-images in advance and adds them to the template before authentication is needed. This preliminary expansion of the template with synthetic fingerprint variations ensures that the template is more complete and robust, reducing authentication failures while maintaining fast authentication speed.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system creates pseudo-images that are copies or synthetic representations of the enrolled fingerprint image. These pseudo-images mimic real fingerprint variations and are added to the template, allowing the system to handle diverse fingerprint presentations without requiring additional physical enrollments.

Inventive Principle:
Principle #26Copying

2Reliability

If the system requires re-enrollment when authentication fails, then authentication reliability is improved, but user convenience deteriorates

Engineering Contradiction:
Improveauthentication reliabilityVSAvoiduser convenience
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The learning unit automatically generates pseudo-images and updates the template without requiring user intervention. The system self-improves its template by creating synthetic fingerprint variations, eliminating the need for users to undergo tedious re-enrollment processes when authentication failures occur.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system proactively expands the template with pseudo-images before authentication failures occur. This preliminary preparation ensures that the template is robust against various fingerprint presentations, preventing authentication failures and avoiding the need for re-enrollment.

Inventive Principle:
Principle #10Preliminary action

3Reliability

If the system collects diverse fingerprint images during enrollment, then template completeness is improved, but enrollment complexity increases

Engineering Contradiction:
Improvetemplate completenessVSAvoidenrollment complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

Instead of requiring users to provide multiple diverse fingerprint images during enrollment, the system creates synthetic copies (pseudo-images) of the enrolled fingerprint. This approach achieves template completeness through computational generation rather than complex data collection procedures.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The learning unit automatically generates the diverse fingerprint variations needed for a complete template without requiring complex user actions. The system self-generates the necessary diversity through pseudo-image creation, simplifying the enrollment process while maintaining template completeness.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP3929808B1Fingerprint authentication device, display device including the same, and method of authenticating fingerprint
Publication Date: 2026.05.06 SAMSUNG DISPLAY CO LTD
  • EP3929808B1 patent drawingFigure 1A
  • EP3929808B1 patent drawingFigure 1B
  • EP3929808B1 patent drawingFigure 2A

AI summary

A fingerprint authentication device includes: a sensor unit configured to output a sensing signal by sensing a fingerprint; an image processing unit configured to generate a fingerprint image based on the sensing signal; a storage unit configured to store a template including an enrolled image; and a learning unit configured to generate a first pseudo image and add the first pseudo image to the template.