Close menu

SURE

Sunderland Repository records the research produced by the University of Sunderland including practice-based research and theses.

Combining Machine Learning Classifiers for the Task of Arabic Characters Recognition

Jaf, Sardar, Alabbas, Maytham and Khudeyer, Raidah S. (2018) Combining Machine Learning Classifiers for the Task of Arabic Characters Recognition. In: International Journal of Asian Language Processing, 2017, Malaysia.

Item Type: Conference or Workshop Item (Paper)

Abstract

There is a number of machine learning algorithms for recognizing Arabic characters. In this paper, we investigate a range of strategies for multiple machine learning algorithms for the task of Arabic characters recognition, where we are faced with imperfect and dimensionally variable input characters. We show two different strategies to combining multiple machine learning algorithms: manual backoff strategry and ensemble learning strategy. We show the performance of using individual algorithms and combined algorithms on recognizing Arabic characters. Experimental results show that combined confidence-based strategies can produce more accurate results than each algorithm produces by itself and even the ones exhibited by the majority voting combination.

[img]
Preview
PDF
Combining Machine Learning Classifiers for the Task of Arabic Characters Recognition.pdf

Download (757kB) | Preview

More Information

Depositing User: Sardar Jaf

Identifiers

Item ID: 10450
URI: http://sure.sunderland.ac.uk/id/eprint/10450
Official URL: http://www.colips.org/journals/volume28/V28_N1_P1....

Users with ORCIDS

Catalogue record

Date Deposited: 05 Mar 2019 10:47
Last Modified: 20 May 2019 11:46

Contributors

Author: Sardar Jaf
Author: Maytham Alabbas
Author: Raidah S. Khudeyer

University Divisions

Faculty of Technology

Subjects

Computing > Data Science
Computing > Artificial Intelligence
Computing > Information Systems
Computing > Programming

Actions (login required)

View Item View Item