Fingerprint Image Resizing Using Inter-Ridge Distance Estimation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing fingerprint verification methods rely on knowing the image resolution, which is not always available, leading to unreliable matching results.

Innovation Solution

An image processing device uses neural networks without normalization layers to estimate inter-ridge distances in fingerprints, generating a local inter-ridge distance map and resizing the image based on estimated distances to match with reference fingerprints, regardless of resolution.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If image resolution is known and used for verification, then matching accuracy is improved, but the method becomes inapplicable when resolution information is unavailable

Engineering Contradiction:

Improvematching accuracyVSAvoidapplicability when resolution unknown

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The system performs self-calibration by automatically estimating its own image resolution through neural network analysis of inter-ridge distances in the fingerprint image, eliminating the need for external resolution metadata or manual calibration inputs

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system changes the parameter representation from fixed resolution-dependent measurements to resolution-independent inter-ridge distance ratios, allowing the same fingerprint features to be verified across different image resolutions without requiring known resolution information

Inventive Principle:

Principle #35Parameter changes

2Adaptability or versatility

If conventional verification methods are used without resolution knowledge, then adaptability is improved, but verification reliability deteriorates

Engineering Contradiction:

Improveverification without resolutionVSAvoidverification reliability

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system replaces traditional resolution-dependent geometric comparison with a neural network-based estimation approach that uses learned patterns of inter-ridge distances to infer resolution and perform verification, achieving both adaptability and reliability

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system introduces an intermediary neural network model that estimates inter-ridge distances and resolves the mismatch between proof and reference images at different resolutions, enabling reliable verification without direct resolution knowledge

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentEP4432256B1Method using pixel inter-peak distances for fingerprints

Publication Date: 2025.11.05 IDEMIA PUBLIC SECURITY FRANCE

Figure 1~2
Figure 3
Figure 4

AI summary

A method for processing a proof image showing a proof fingerprint, the method comprising the following computer-implemented steps: estimating (118) a first proof inter-ridge distance relating to the proof fingerprint, the first proof inter-ridge distance being a distance in pixels; obtaining (120) a reference inter-ridge distance relating to a reference fingerprint shown in a reference image, the reference inter-ridge distance being a distance in pixels; resizing (122) the proof image into a resized proof image such that the first proof inter-ridge distance in pixels corresponds to the reference inter-ridge distance in pixels; and commanding (124) a comparison between the resized proof image and the reference image, so as to verify a match between the proof fingerprint and the reference fingerprint.