Related Experiment Video
Updated: Mar 19, 2026
05:58
Digital Handwriting Analysis of Characters in Chinese Patients with Mild Cognitive Impairment
Published on: March 11, 2021
5.2K
A Behavioral Handwriting Model for Static and Dynamic Signature Synthesis
Summary
This study introduces a novel method for synthesizing both static and dynamic handwritten signatures using motor equivalence theory. The approach enhances biometric applications by creating realistic signature forgeries and diverse training datasets.
Area of Science:
- Biometrics
- Computer Science
- Human-Computer Interaction
Background:
- Motor equivalence theory explains handwriting as cognitive and motor levels.
- Previous methods synthesized static signatures using engrams and kinematic filters.
- There is a need for dynamic signature synthesis in biometrics.
Purpose of the Study:
- To develop a unified synthesizer for both static and dynamic handwritten signatures.
- To incorporate dynamic information, including pen-ups, into signature synthesis.
- To evaluate the synthesizer's adaptability to signature variability for biometric applications.
Main Methods:
- Utilizing motor equivalence theory for signature generation.
- Implementing lognormal sampling for dynamic trajectory analysis, including pen-ups.
- Employing perceptual relevance and interpolation for forgery imitation.
Main Results:
- Successful synthesis of both static and dynamic signatures with a unified model.
- Demonstrated adaptability to inter- and intra-personal signature variability.
- Promising results indicating potential beyond biometric database generation.
Conclusions:
- The proposed synthesizer effectively generates realistic static and dynamic signatures.
- The method shows potential for diverse applications, including advanced biometric systems.
- Further research can explore broader applications of this unified signature synthesis model.
