Fingerprint Template Learning for Dry-Skin Display Authentication
Find Innovative SolutionsGenerate 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
Engineering 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
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.
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.
2Reliability
If the system requires re-enrollment when authentication fails, then authentication reliability is improved, but user convenience deteriorates
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.
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.
3Reliability
If the system collects diverse fingerprint images during enrollment, then template completeness is improved, but enrollment complexity increases
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.
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.
Data Source
Figure 1A
Figure 1B
Figure 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.