Title: Offline writer identification using Latin and Arabic scripts: a comprehensive literature review and perspectives

Authors: Yaacoub Hannad; Abdelillah Semma

Addresses: Faculty of Educational Sciences, Mohammed V University of Rabat, Rabat, 10000, Morocco ' Faculty of Sciences, Ibn Tofail University, Kenitra, 14000, Morocco

Abstract: Handwriting-based writer identification has been recognised as a reliable aspect of behavioral biometrics. This paper provides a comprehensive review of established offline writer identification systems in the independent text mode. It aims to present the current state of writer identification methods and identify potential avenues for advancing this research field. The paper elucidates the typical architectural framework employed in offline writer identification systems and provides an overview of the most prevalent handwritten databases containing Latin and Arabic samples. A key contribution of this work is presenting state-of-the-art approaches in chronological order, contrasting with existing publications, to stimulate interest among new researchers and facilitate their exploration of this field. This work is intended to serve as a valuable resource for aspiring researchers seeking to enter the field of writer identification, while actively enhancing our understanding of current writer identification methods and propelling advancements within this research domain.

Keywords: writer identification survey; handwriting analysis; Latin and Arabic script; offline systems; behavioural biometric; handwritten database; literature review; writer identification methods.

DOI: 10.1504/IJSISE.2024.143820

International Journal of Signal and Imaging Systems Engineering, 2024 Vol.13 No.3, pp.157 - 185

Received: 09 Feb 2024
Accepted: 05 Sep 2024
Published online: 08 Jan 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article