Please use this identifier to cite or link to this item:
Title: Using calligraphies features for off line writer identification
Authors: Vásquez, José L.
Travieso, Carlos M. 
Alonso, Jesús B. 
UNESCO Clasification: 3307 Tecnología electrónica
Keywords: Writing , Feature extraction , Training , Forensics , Databases , Support vector machines , Educational institutions, Writer Identification , Off-line Handwriting , Graphology Techniques , SVM , Biometrics , Patter Recognition
Issue Date: 2013
Publisher: 1071-6572
Journal: Proceedings - International Carnahan Conference on Security Technology 
Conference: 2013 47th International Carnahan Conference on Security Technology, ICCST 2013 
Abstract: This work proposes an off-line writer identification approach based on graphometrical and forensic features. We selected a set of features with independence of the text and some stability degree to natural changes in the writing. The system uses the LS-SVM classifier with RBF kernel, reaching up to 99.1% of success rate for an own database composed by 100 users with 10 samples per each one
ISBN: 9781479908899
ISSN: 1071-6572
DOI: 10.1109/CCST.2013.6922062
Source: Proceedings - International Carnahan Conference on Security Technology[ISSN 1071-6572] (6922062)
Appears in Collections:Actas de congresos
Show full item record


checked on Feb 28, 2021

Page view(s)

checked on Mar 1, 2021

Google ScholarTM




Export metadata

Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.