Iterative Minutiae Grouping for Distorted Fingerprint Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional fingerprint matchers struggle to accurately identify corresponding minutiae pairs in distorted regions due to differences in rotation and translation parameters, leading to inaccurate match results when distorted areas are significant.
Innovation Solution
An iterative minutiae matching technique that groups mated minutiae based on similar rotation and translation parameters, performing a geometric consistency check to improve the identification of globally aligned minutiae and enhance the similarity score calculation between reference and search fingerprints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional fingerprint matchers use a two-stage matching process with local and global matching of minutiae, then the matching process is computationally efficient and simple, but the accuracy of identifying corresponding minutiae pairs in distorted regions deteriorates due to differences in rotation and translation parameters
Solution Approach 1:
The patent segments the fingerprint matching process into multiple iterative rounds, where each round identifies and removes a subset of globally aligned minutiae pairs. This segmentation allows the system to handle distorted regions by processing minutiae in groups with similar rotation and translation parameters, thereby improving identification accuracy while maintaining computational efficiency through structured division of the matching task.
Solution Approach 2:
The patent implements a dynamic iterative matching process where the set of candidate minutiae pairs is updated in each round by removing identified globally aligned pairs. This dynamic approach allows the system to adapt to distorted regions by progressively refining the matching results, adjusting the parameter sets (rotation and translation) in each iteration to accommodate local variations in the fingerprint structure.
2Device complexity
If traditional fingerprint matchers omit matching of minutiae within distorted regions to maintain processing speed, then the computational complexity remains low, but the reliability of fingerprint matching deteriorates when distorted areas are significantly large
Solution Approach 1:
The patent applies partial action by identifying and processing only the subset of minutiae pairs that exhibit global alignment characteristics in each iterative round, rather than attempting to process all minutiae simultaneously. This approach handles distorted regions effectively by focusing computational resources on confidently matched pairs while maintaining low processing complexity through selective, incremental processing of the minutiae set.
3Measurement precision
If an iterative minutiae matching technique groups mated minutiae and performs geometric consistency checks, then the identification accuracy of globally aligned minutiae in distorted regions improves, but the computational time and processing complexity increase
Solution Approach 1:
The patent performs preliminary grouping of mated minutiae based on similar rotation and translation parameters before conducting geometric consistency checks. This preliminary organization reduces the computational burden during the iterative matching process by pre-categorizing candidate pairs, allowing the system to efficiently identify globally aligned minutiae while minimizing the time penalty associated with enhanced accuracy measures.
Data Source
AI summary
In some implementations, a computer-implemented method includes an iterative minutiae matching technique that initially groups mated minutiae within a list of all possible minutiae between a reference fingerprint and a search fingerprint, and then successively performs a geometric consistency check of the mated minutiae within the group. In some instances, the iterative matching technique enables improved identification of globally aligned mated minutiae within distorted regions, which may be used to subsequently improve the calculation of a similarity score between a reference fingerprint and a search fingerprint.