Fingerprint Verification Using Segmented Partial Image Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current fingerprint verification methods face challenges in efficiently matching partial fingerprint images due to variations in rotation, translation, and image quality, leading to reduced accuracy and increased computational complexity.
Innovation Solution
The method involves selecting fingerprint groups based on similarities using the Fourier-Mellin method for phase correlation and normalized cross-correlation, determining representative values, and calculating scores to verify successful matching, thereby improving accuracy and reducing processing load.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional fingerprint matching methods are used to compare input fingerprint image with all enrolled fingerprint images, then verification accuracy can be maintained, but computational complexity increases and processing time extends
Solution Approach 1:
The patent segments the enrolled fingerprint database into multiple fingerprint groups based on classification information (such as finger type, user category, or other attributes). Instead of comparing the input fingerprint image with all enrolled images, the system only compares it with images in the relevant group(s), significantly reducing computational complexity while maintaining verification accuracy through targeted matching.
2Reliability
If fingerprint verification compares entire fingerprint images, then comprehensive matching is achieved, but processing time increases due to handling variations in rotation, translation, and image quality
Solution Approach 1:
The patent divides both the input fingerprint image and enrolled fingerprint images into multiple partial fingerprint images (sub-regions). By comparing corresponding partial images rather than entire images, the system reduces processing time and computational load while improving reliability through focused comparison of specific fingerprint features, thereby addressing variations in rotation, translation, and quality more effectively.
Data Source
AI summary
A fingerprint verification method includes selecting one or more first fingerprint groups from among a plurality of fingerprint groups based on an input fingerprint image, each fingerprint group of the plurality of fingerprint groups including partial fingerprint images; and determining whether verification is successful based on the input fingerprint image and each of the partial fingerprint images included in the one or more first fingerprint groups.