Page 81 - 2024-Vol20-Issue2

Received: 20 August 2023 | Revised: 10 September 2023 | Accepted: 14 September 2023

DOI: 10.37917/ijeee.20.2.7 Vol. 20 | Issue 2 | December 2024

Open Access

Iraqi Journal for Electrical and Electronic Engineering

Original Article

Handwritten Signature Verification Method Using

Convolutional Neural Network

Wijdan Yassen A. AlKarem*, Eman Thabet Khalid, Khawla. H. Ali
Department of Computer Sciences, Education College for Pure Sciences, University of Basrah, Basrah, Iraq

Correspondance
*Wijdan Yassen A. AlKarem
Department of Computer Sciences,
Education College for Pure Sciences,
University of Basrah, Basrah, Iraq.
Email: wijdan.abdalkarem@uobasrah.edu.iq

Abstract
Automatic signature verification methods play a significant role in providing a secure and authenticated handwritten
signature in many applications, to prevent forgery problems, specifically institutions of finance, and transections of
legal papers, etc. There are two types of handwritten signature verification methods: online verification (dynamic)
and offline verification (static) methods. Besides, signature verification approaches can be categorized into two styles:
writer dependent (WD), and writer independent (WI) styles. Offline signature verification methods demands a high
representation features for the signature image. However, lots of studies have been proposed for WI offline signature
verification. Yet, there is necessity to improve the overall accuracy measurements. Therefore, a proved solution in this
paper is depended on deep learning via convolutional neural network (CNN) for signature verification and optimize the
overall accuracy measurements. The introduced model is trained on English signature dataset. For model evaluation, the
deployed model is utilized to make predictions on new data of Arabic signature dataset to classify whether the signature
is real or forged. The overall obtained accuracy is 95.36% based on validation dataset.

Keywords
Authentication , Convolutional neural network, Handwritten signature , Offline signature , Verification ,Writer
independent (WI).

I. INTRODUCTION ness, pressure [2]. On the other hand, offline signature veri-
fication and recognition methods use an ordinary procedure
Handwritten signature verification has gained a considerable by signing a paper by a pen and then the image of signature
amount of interest in the latest research, in terms of dealing is scanned and fed to a classifier to verify the signature [2–6].
with issues of authentication and fraud. Signature verification Despite witnessed developments in technology lately, an of-
is an essential to authorize individual identity. Handwritten fline signature verification system is still necessary in many
signature verification is a crucial task to prevent forgery prob- countries that are still depends on paper works in their deal-
lems that could lead to bad outcomes [1]. There are two types ings. Offline signature verification is a difficult issue, since
of handwritten signature verification and recognition meth- no dynamic features come from sensing devices are available
ods: online verification (dynamic) [2] and offline verification like in online signature. Extracting sophisticated features for
(static) methods [3]. An online signature verification method offline signature verification is challenging [6–9]. This paper
utilizes an electronic signature based on particular devices proposes an offline signature verification method to verify
such as pressure sensing of mobile phones, digitizers, and whether the input signature is real or forged. Besides, signa-
smart pens. Online methods use the dynamic features of a ture verification approaches can be categorized into two styles:
handwritten signature such as order of strikes, time, speedi- writer dependent (WD) [9, 10], and writer independent (WI)

This is an open-access article under the terms of the Creative Commons Attribution License,
which permits use, distribution, and reproduction in any medium, provided the original work is properly cited.
©2024 The Authors.
Published by Iraqi Journal for Electrical and Electronic Engineering | College of Engineering, University of Basrah.

https://doi.org/10.37917/ijeee.20.2.7 |https://www.ijeee.edu.iq 77