Biometric Authentication Device Using Minutia and Pattern Matching

Solution Overview

Problem

Biometric authentication methods using either minutia matching or pattern matching face limitations, such as high verification rates but long times for minutia matching and low verification rates with long times for pattern matching, making them unsuitable for one-to-many verification and unclear images, respectively.

Innovation Solution

A biometric information authentication device that combines both minutia and pattern matching methods by extracting and verifying data from fingerprint images using both techniques, with threshold-based decision-making to determine the appropriate method for verification, allowing for high-speed verification and unfailing authentication without increasing overall time.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If minutia matching method is used for authentication, then verification rate is improved and verification time is reduced, but authentication capability for unclear images deteriorates

Engineering Contradiction:

Improveverification rateVSAvoidauthentication capability for unclear images

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The authentication process is segmented into two independent pathways: one for clear images using minutia matching method and another for unclear images using pattern matching method. The system determines which pathway to follow based on image quality assessment, allowing each method to operate optimally on suitable inputs without forcing both methods to process all images.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system dynamically switches between minutia matching method and pattern matching method based on the quality of the input image. The determination unit assesses image quality in real-time and adapts the authentication approach accordingly, making the system flexible and responsive to varying image conditions rather than using a fixed single method.

Inventive Principle:

Principle #15Dynamics

2Reliability

If pattern matching method is used for authentication, then authentication capability for unclear images is improved, but verification rate deteriorates and verification time increases

Engineering Contradiction:

Improveauthentication capability for unclear imagesVSAvoidverification rate

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The authentication process is segmented into two independent pathways: one for clear images using minutia matching method and another for unclear images using pattern matching method. The system determines which pathway to follow based on image quality assessment, allowing each method to operate optimally on suitable inputs without forcing both methods to process all images.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Instead of applying pattern matching method to all images (excessive action), the system applies it only to unclear images where it is needed (partial action). This selective application maintains high verification rates for clear images while providing reliable authentication for unclear images, avoiding the waste of computational resources on images that can be processed more efficiently by minutia matching.

Inventive Principle:

Principle #16Partial or excessive action

3Reliability

If both minutia matching method and pattern matching method are used for authentication, then authentication accuracy is improved, but verification time increases

Engineering Contradiction:

Improveauthentication accuracyVSAvoidverification time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The authentication process is segmented into two independent pathways: one for clear images using minutia matching method and another for unclear images using pattern matching method. The system determines which pathway to follow based on image quality assessment, allowing each method to operate optimally on suitable inputs without forcing both methods to process all images.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Instead of applying pattern matching method to all images (excessive action), the system applies it only to unclear images where it is needed (partial action). This selective application maintains high verification rates for clear images while providing reliable authentication for unclear images, avoiding the waste of computational resources on images that can be processed more efficiently by minutia matching.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS7526110B2Biometric information authentication device, biometric information authentication method, and computer-readable recording medium with biometric information authentication program recorded thereon

Publication Date: 2009.04.28 FUJITSU LTD

AI summary

For personal authentication using biometric information, to allow for unfailing authentication without increasing verification time even for an authentication object that is not supported only by a minutia matching method, the present invention provides a biometric information authentication device comprising: a first verifying section for verifying first to-be-verified data against first registration data registered preliminarily using a minutia matching method; a second verifying section for verifying second to-be-verified data against second registration data registered preliminarily using a pattern matching method; and a determining section for comparing match degree, which is obtained as a result of verification by the first verifying section, with a first threshold value and a second threshold value to allow the second verifying section to perform verification in the case where the match degree is equal to or smaller than the first threshold value and equal to or larger than the second threshold value.