Automated Offline Arabic Signature Verification System using Multiple Features Fusion for Forensic Applications

Journal Title: Arab Journal of Forensic Sciences & Forensic Medicine - Year 2016, Vol 1, Issue 4

Abstract

The signature of a person is one of the most popular and legally accepted behavioral biometrics that provides a secure means for verification and personal identification in many applications such as financial, commercial and legal transactions. The objective of the signature verification system is to classify between genuine and forged signatures that are often associated with intrapersonal and interpersonal variability. Unlike other languages, Arabic has unique features; it contains diacritics, ligatures, and overlapping. Because of lacking any form of dynamic information during the Arabic signature’s writing process, it will be more difficult to obtain higher verification accuracy. This paper addresses the above difficulty by introducing a novel offline Arabic signature verification algorithm. The key point is using multiple feature fusion with fuzzy modeling to capture different aspects of a signature individually in order to improve the verification accuracy. State-of-the-art techniques adopt the fuzzy set to describe the properties of the extracted features to handle a signature’s uncertainty; this work also employs the fuzzy variables to describe the degree of similarity of the signature’s features to deal with the ambiguity of questioned document examiner judgment of signature similarity. It is concluded from the experimental results that the verification system performs well and has the ability to reduce both False Acceptance Rate (FAR) and False Rejection Rate (FRR)

Authors and Affiliations

Saad M. Darwish, Ashraf M. El-Nour

Keywords

Related Articles

Paternity Cases within a Medicolegal Context: a Case Study of Heteropaternal Superfecundation in Iraq

A case of paternity was referred to the Medical-Legal Directorate( MLD)/ Baghdad in August 2011 .The family who were concerned was the Father (41 years old ) ,mother (23 years old) and 2 sons non identical twin (1.5year...

Postmortem Biochemistry and Toxicology

The aim of postmortem biochemistry and toxicology is either to help establish the cause of death, or to gain information on events immediately before death. If self-poisoning is suspected, the diagnosis may be straightfo...

Sexual Dimorphism and Estimation of Height from Body Length Anthropometric Parameters among the Hausa Ethnic Group of Nigeria

The study was carried out to investigate the sexual dimorphism in length and other anthropometric parameters. To also generate formulae for height estimation using anthropometric measurements of some length parameters am...

The Evidentiary Value of DNA Fingerprint as Criminal Evidence

The subject of criminal evidence is considered to be one of the greatest challenges that face authorities concerned with fighting crime at all levels. Due to this, authorities try to benefit as much as possible from scie...

3rd International Arab Forensic Sciences & Forensic Medicine Conference, ASFSFM 2017: Conference Report

The Arab Society for Forensic Sciences and Forensic Medicine (ASFSFM) at Naif Arab University for Security Sciences seeks to present the latest developments in all fields of forensic sciences through holding specialized...

Download PDF file
  • EP ID EP279021
  • DOI 10.12816/0033136
  • Views 101
  • Downloads 0

How To Cite

Saad M. Darwish, Ashraf M. El-Nour (2016). Automated Offline Arabic Signature Verification System using Multiple Features Fusion for Forensic Applications. Arab Journal of Forensic Sciences & Forensic Medicine, 1(4), -. https://europub.co.uk/articles/-A-279021