Modeling Stability in On-line Signatures

Authors

  • Antonio Parziale Natural Computation Lab - Department of Information Engineering, Electrical Engineering and Applied Mathematics - University of Salerno
  • Salvatore G. Fuschetto Natural Computation Lab - Department of Information Engineering, Electrical Engineering, and Applied Mathematics - University of Salerno
  • Angelo Marcelli Natural Computation Lab - Department of Information Engineering, Electrical Engineering, and Applied Mathematics - University of Salerno

DOI:

https://doi.org/10.31974/jfde24-37-46

Keywords:

Signature verification, Stability, Handwriting generation

Abstract

A novel definition of stability regions and a new method for detecting them from on-line signatures is introduced in this paper. Building upon handwriting generation and motor control studies, the stability regions is defined as the longest similar sequences of strokes between a pair of genuine signatures. The stability regions are then used to select the most stable signatures, as well as to estimate the extent to which these stability regions are encountered in both genuine and simulated (forged) signatures, thus modeling the signing habit of a subject. Experimental results on the SUSig database show that the proposed model can be effectively used for signature verification.

Purchase Article for $10 

Downloads

Published

2014-12-31

How to Cite

Parziale, A., Fuschetto, S. G., & Marcelli, A. (2014). Modeling Stability in On-line Signatures. Journal of Forensic Document Examination, 24, 37–46. https://doi.org/10.31974/jfde24-37-46

Issue

Vol. 24 (2014): Journal of Forensic Document Examination

Section

Research Papers

License

©2024 Journal of Forensic Document Examination (JFDE). All rights reserved.  Written permission must be obtained from the editor of the JFDE at journal.jfde@gmail.com before copying, transmitting, storing, printing, or using for any other means.  Authors may copy their article for educational and research purposes exclusively, retain the research data, and receive proper attribution and credit for their work.