Fingerprint Identification Using Minutia Surrounding Features
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing fingerprint identification algorithms based on minutia matching have low accuracy when dealing with partial fingerprints due to the small number of minutiae and limited overlapping area, leading to difficulties in distinguishing different fingers and the same finger.
Innovation Solution
The proposed method captures fingerprints using a sensor, identifies matching pairs of minutiae, calculates a first matching result, and then determines whether the surrounding features of the captured minutiae match those of a reference fingerprint, generating a second matching result to improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If fingerprint identification is based on minutia matching, then the algorithm has low complexity and small memory requirements, but the accuracy is low when dealing with partial fingerprints
Solution Approach 1:
The algorithm segments the fingerprint matching process into two independent stages: minutia feature matching (first matching result) and minutia surrounding feature matching (second matching result). This segmentation allows the system to maintain low complexity in the first stage while adding accuracy improvements in the second stage without significantly increasing overall computational burden
Solution Approach 2:
The minutia surrounding features (including direction strength, binary pixel information, and gray information) serve as intermediary elements that bridge the gap between simple minutia matching and complex full fingerprint analysis. These intermediary features provide additional discrimination power for partial fingerprints while requiring minimal additional computational resources
2Area of stationary object
If the fingerprint sensor area is small, then the device size is reduced, but the number of collected minutiae is insufficient leading to low identification accuracy
Solution Approach 1:
The algorithm changes the parameter set used for matching by incorporating minutia surrounding features (direction strength, binary pixel information, gray information) in addition to traditional minutia features. This parameter expansion enables accurate identification even when the number of minutiae is limited due to small sensor area
Solution Approach 2:
The algorithm adds another dimension to the matching process by considering surrounding features of minutiae, not just the minutiae themselves. This dimensional expansion provides more discrimination power for distinguishing different fingers when working with partial fingerprints from small sensors
Data Source
AI summary
The present disclosure relates to a fingerprint identification method, device, an electronic apparatus and a storage medium. The fingerprint identification method includes: capturing a fingerprint by a fingerprint sensor, identifying matching pairs of minutiae between the captured fingerprint and a reference fingerprint; calculating a first matching result based on the minutia matching pairs; identifying minutia surrounding features for each minutia of the captured fingerprint in the minutia matching pairs; determining, for each minutia in the minutia matching pairs, whether the minutia surrounding features of the captured fingerprint match with minutia surrounding features of the reference fingerprint; calculating a second matching result based on the determination; and generating an identification result based on the first matching result and the second matching result.