Segment-Block Handwritten Signature Authentication

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current handwritten signature authentication systems face challenges in accurately distinguishing between genuine and forged signatures, particularly when behavioral characteristics are copied, leading to potential identity theft and compromised security.

Innovation Solution

A segment-block-based handwritten signature authentication system that extracts and compares characteristics information from disjointed segments of a signature, including overall block and segment block features, to enhance recognition accuracy by analyzing correlations between segments and the overall signature block.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If behavioral characteristics data comparison method is used for handwritten signature authentication, then individual characteristics of each user can be considered, but a third party can copy the behavioral characteristics to some extent when copying a handwritten signature image

Engineering Contradiction:
Improveauthentication accuracyVSAvoididentity theft risk
Core Design Contradiction:
ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The patent divides the handwritten signature into multiple segments based on lifting points (where the pen is lifted from the surface). Each segment is analyzed separately to extract behavioral characteristics. This segmentation makes it difficult for forgers to replicate the signature because they cannot easily copy the dynamic behavioral characteristics of each segment, only the static image.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent extracts specific behavioral characteristics from each segment, such as pressure, speed, acceleration, and timing information. By isolating and analyzing these specific characteristics separately, the system can detect subtle differences that indicate forgery, even when the overall signature image appears similar.

Inventive Principle:
Principle #2Taking out (Extraction)

2Ease of operation

If traditional handwritten signature authentication system determines match based on similar behavioral characteristics, then authentication can be performed, but the system determines that two signatures match even when the images of the two signatures are completely different

Engineering Contradiction:
Improveauthentication processVSAvoidsignature recognition accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

By segmenting the signature and analyzing behavioral characteristics of each segment separately, the system achieves more precise matching. The segmentation allows for detailed comparison of pressure, speed, and timing patterns in each segment, leading to more accurate authentication decisions.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies different analysis methods to different segments of the signature. Each segment's behavioral characteristics are evaluated with local quality metrics, allowing the system to capture nuanced differences in various parts of the signature that contribute to overall authentication accuracy.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP3370181B1Segment-block-based handwritten signature authentication system and method
Publication Date: 2023.08.23 SECUVE CO LTD

AI summary

The present invention relates to a handwritten signature authentication system and method and, more specifically, to a handwritten signature authentication system and method which register a handwritten signature including handwritten signature characteristics information based on segments distinguished by strokes made by a user when the user handwrites the signature, obtain the segment-based handwritten signature characteristics information from the handwritten signature written by the user upon request for handwritten signature authentication, and perform handwritten signature authentication by comparing the obtained segment-based handwritten signature characteristics information with pre-registered segment-based handwritten signature characteristics information.