Biometric Template Segmentation for Dynamic Fingerprint Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Biometric recognition devices face challenges in matching fingerprint images over time due to changes in skin conditions, such as the development of calluses or moisture level changes, which affect the accuracy of fingerprint matching.
Innovation Solution
A biometric recognition device template is updated with a short term component for recently captured nodes and a long term component, where nodes are stored based on their coverage area, matchability, and age, allowing for dynamic adjustment and storage of new nodes in both components to maintain accurate fingerprint recognition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single static template is stored for fingerprint recognition, then the device complexity is reduced, but the recognition reliability deteriorates over time due to skin changes
Solution Approach 1:
The template is segmented into multiple nodes representing different portions of the fingerprint, organized into short-term and long-term components. This segmentation allows the system to track changes in specific fingerprint regions independently, maintaining recognition reliability while managing complexity through structured organization.
Solution Approach 2:
The template structure transitions from static to dynamic by incorporating time-based components (short-term and long-term) that adapt to skin changes. The system dynamically updates nodes based on their age and matchability, allowing the template to evolve with the user's fingerprint characteristics over time.
2Reliability
If multiple templates are stored for each user to account for fingerprint variations, then the recognition reliability is improved, but the device complexity increases
Solution Approach 1:
Instead of storing multiple complete templates, the system segments a single template into multiple nodes that can independently represent different fingerprint portions. This segmentation provides the flexibility of multiple templates while maintaining a unified template structure, reducing overall complexity.
Solution Approach 2:
The system adds a time dimension to the template structure by creating short-term and long-term components. This dimensional transformation allows the template to capture temporal variations in fingerprint characteristics without requiring multiple separate templates, managing complexity through temporal organization.
3Reliability
If the template is updated frequently with new fingerprint captures, then the recognition reliability is maintained despite skin changes, but the loss of time for processing increases
Solution Approach 1:
The system performs partial updates by selectively updating only certain nodes in the template based on their age and matchability characteristics. This partial action approach maintains recognition reliability for critical fingerprint regions while reducing the time investment required for complete template updates.
Solution Approach 2:
The system uses feedback from node matchability assessments to determine which nodes require updating. By evaluating node characteristics and selectively updating only those that need refinement, the system maintains reliability while minimizing processing time through intelligent update decisions.
Data Source
AI summary
A template of a biometric attribute for use with a biometric recognition device includes a long term component and a short term component. The long term component can include a plurality of nodes that each represents at least a portion of the biometric attribute. The short term component may include one or more newly captured nodes that each represents at least a portion of the biometric attribute.