Off-line writer identification using multi-scale local binary patterns and SR-KDA

Khalifa, E., Al-Maadeed, Somaya, Tahir, Muhammad, Khelifi, Fouad and Bouridane, Ahmed (2013) Off-line writer identification using multi-scale local binary patterns and SR-KDA. In: 2013 25th International Conference on Microelectronics (ICM). IEEE, Piscataway, NJ, pp. 1-4. ISBN 978-1-4799-3569-7

Full text not available from this repository. (Request a copy)

Abstract

Writer identification is becoming an increasingly important research topic especially in forensic and biometric applications. This paper presents a novel method for performing offline write identification by using multi-scale local binary patterns histogram (MLBPH) features. The proposed feature (MLBPH) when combined with edge-hinge based feature achieves a top 1 recognition rate of 92% on the benchmark IAM English handwriting dataset, outperforming current state of the art features. Further, kernel discriminant analysis using spectral regression (SR-KDA) is introduced as dimensionality reduction technique to avoid the overfitting problem associated with using multi-scale data.

Item Type:	Book Section
Uncontrolled Keywords:	Writer Identification, kernel discriminant analysis, multi-scale local binary patterns
Subjects:	G400 Computer Science
Department:	Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User:	Becky Skoyles
Date Deposited:	08 May 2014 10:26
Last Modified:	12 Oct 2019 22:29
URI:	http://nrl.northumbria.ac.uk/id/eprint/16399

Downloads