Int. J. Computer Applications in Technology, Vol. 63, Nos. 1/2, 2020 83
Copyright © 2020 Inderscience Enterprises Ltd.
Arabian horse identification based on whale
optimised multi-class support vector machine
Ayat Taha*
Faculty of Science,
Al-Azhar University,
Cairo, Egypt
Email: ayat_taha@ymail.com
*Corresponding author
Ashraf Darwish
Faculty of Science,
Helwan University,
Cairo, Egypt
Email: ashraf.darwish.eg@ieee.org
Aboul Ella Hassanien
Faculty of Computers and Information,
Cairo University,
Cairo, Egypt
Email: aboitcairo@gmail.com
Ahmed ElKholy
Faculty of Science,
Al-Azhar University,
Cairo, Egypt
Email: AhmedElkholySc@yahoo.com
Abstract: In this study, a biometric identification approach for Arabian horse identification is
proposed based on the optimised Multi-Class Support Vector Machine (MCSVM). The
identification approach is performed in three phases: feature extraction, classification, and
optimisation. The feature extraction phase uses Histogram of Oriented Gradient (HOG) to extract
features vectors from muzzle print images of the Arabian horses and then stored in the database
with its labels. The second phase is the classification phase which uses MCSVM for training and
testing classification. Finally in the optimised MCSVM phase, three different swarms, Particle
Swarm Optimisation (PSO), Grey Wolf Algorithm (GWA) and Whale Optimisation (WO), are
used to optimise MCSVM parameters to enhance the identification accuracy of the Arabian
horse. The results obtained show that the MCSVM achieves accuracy of 93.2% and increases to
97.4% with WO algorithm which achieves the best accuracy compared to PSO and GWA.
Keywords: Arabian horse identification; histogram of oriented gradient; multi-class support
vector machine; whale optimisation algorithm.
Reference to this paper should be made as follows: Taha, A., Darwish, A., Hassanien, A.E. and
ElKholy, A. (2020) ‘Arabian horse identification based on whale optimised multi-class support
vector machine’, Int. J. Computer Applications in Technology, Vol. 63, Nos. 1/2, pp.83–92.
Biographical notes: Ayat Taha received her BSc in 2010 and MSc degree in 2015, both from
Al-Azhar University, Faculty of Science, Pure Mathematics and Computer Science Department, Cairo,
Egypt. On March 2017, she pursued her PhD program from the Department of Computer Science at
Science faculty, Al-Azhar University. She is Assistant Lecture of a computer science at the Cairo
Institute for Computer Science and Commercial Sciences and a member of the Egyptian Scientific
Research Group in Egypt (SRGE). Her research areas include biometrics, computer vision, image
processing, pattern recognition and artificial intelligence, metaheuristic, machine learning, and deep
learning.
Ashraf Darwish is Associate Professor of Computer Science and Acting the Head of Mathematics
and Computer Science Department at Faculty of Science, Helwan University, Egypt. He received
the PhD degree in computer science from Saint Petersburg State University, Russian Federation
in 2006. He received a BSc and MSc in Mathematics from Faculty of Science, Tanta University,