A set of geometrical features for writer identification

Hassaine, Abdelaali, Al-Maadeed, Somaya and Bouridane, Ahmed (2012) A set of geometrical features for writer identification. In: Neural Information Processing. Springer, London, pp. 584-591. ISBN 978-3-642-34499-2

Full text not available from this repository. (Request a copy)
Official URL: http://dx.doi.org/10.1007/978-3-642-34500-5_69

Abstract

Writer identification is an important field in the forensic document examination. We propose in this paper a set of geometrical features that makes it possible to characterize writers. They include directions, curvatures and tortuosities. We show how these features can be combined with edge based directional features as well as chain code based features. Evaluation of the method is performed on the IAM handwriting database.

Item Type: Book Section
Uncontrolled Keywords: Forensic document examination, handwriting curvatures, handwriting directions, handwriting tortuosities, writer identification
Subjects: G400 Computer Science
Department: Faculties > Engineering and Environment > Computer Science and Digital Technologies
Depositing User: Becky Skoyles
Date Deposited: 22 Jan 2015 10:06
Last Modified: 10 Nov 2016 12:40
URI: http://nrl.northumbria.ac.uk/id/eprint/20709

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics


Policies: NRL Policies | NRL University Deposit Policy | NRL Deposit Licence