Stripe Pattern Image Collating Device for Latent Fingerprint Matching

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

High-quality fingerprint images can achieve accurate feature point extraction, but latent fingerprints with small feature point areas struggle to match accurately due to insufficient feature points, leading to poor collation scores when opposite feature point pairs are not extracted correctly.

Innovation Solution

A stripe pattern image collating device that includes a feature extracting unit for extracting feature points and skeletons from both images, a skeleton collating unit for calculating collation scores, and an image analyzing unit to correct scores by analyzing areas with unpaired feature points, improving matching accuracy by utilizing opposite feature point pairs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If feature point extraction is performed on latent fingerprint images with small feature point areas, then the collation process can be completed, but the number of extractable feature points is insufficient leading to poor collation accuracy

Engineering Contradiction:

Improvecollation accuracyVSAvoidnumber of feature points

Core Design Contradiction:

Measurement precisionVSQuantity of substance

Solution Approach 1:

The patent transitions from two-dimensional feature point matching to three-dimensional ridge structure analysis. By extracting ridge line skeletons and analyzing ridge patterns in the third dimension (depth/structure), the system can identify matching features even when traditional 2D feature points are insufficient in small area latent fingerprints.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The patent changes the parameters used for collation from relying solely on feature point coordinates to incorporating ridge pattern characteristics, ridge orientation, and skeleton structure parameters. This parameter transformation enables accurate matching by utilizing different measurable properties that remain valid even when feature point quantity is limited.

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If manual input of feature points is performed for latent fingerprints, then collation can proceed with sufficient feature points, but the process time and operational complexity increase

Engineering Contradiction:

Improvecollation accuracyVSAvoidfeature point input time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs automatic feature extraction and ridge skeleton generation without requiring examiner intervention. The automated processing extracts ridge patterns and generates skeleton data autonomously, eliminating the time-consuming manual feature point input while maintaining collation accuracy through algorithmic analysis of ridge structures.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual operation of feature point input with an automated computer-based image processing system. By substituting human examiner operations with algorithmic ridge analysis and skeleton extraction, the system achieves both time efficiency and consistent accuracy without manual intervention.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Ease of operation

If traditional feature point collation is used for latent fingerprints, then the process is simple, but unpaired feature points cause deterioration of collation scores

Engineering Contradiction:

Improvecollation process simplicityVSAvoidcollation score

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent segments the fingerprint analysis into multiple independent components: ridge extraction, skeleton generation, feature point identification, and pattern matching. This segmentation allows the system to process each component separately and identify unpaired feature points through systematic comparison, maintaining operational simplicity while improving score accuracy through structured analysis.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system implements feedback mechanisms where collation results are continuously refined by analyzing ridge patterns and skeleton structures. Unpaired feature points are identified through feedback from the matching process, and the collation score is adjusted based on ridge pattern similarity, creating a self-correcting system that maintains simplicity while improving precision.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS12033427B2Stripe pattern image collating device, stripe pattern collating method, and computer-readable medium storing program thereof

Publication Date: 2024.07.09 NEC CORP

AI summary

A stripe pattern image collating device according to the example embodiment includes a feature extracting unit that extracts a feature point and a skeleton from a first stripe pattern image and a second stripe pattern image in which a stripe pattern is formed of ridges, and generates feature point data and skeleton data. A skeleton collating unit that collates two sets of pieces of the feature point data and pieces of the skeleton data that are extracted from each of the first stripe pattern image and the second stripe pattern image, and calculates a collation score. An image analyzing unit that analyzes the second stripe pattern image with respect to an area in which an opposite feature point pair of the first stripe pattern image exists, calculates an image analysis score, and corrects the collation score.