ISSN 2303-4521
Periodicals of Engineering and Natural Sciences Original Research
Vol. 10, No. 2, April 2022, pp.500-511
© The Author 2022. This work is licensed under a Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) that
allows others to share and adapt the material for any purpose (even commercially), in any medium with an acknowledgement of the work's
authorship and initial publication in this journal.
500
Descriptor feature based on local binary pattern for face classification
Seba Aziz Sahy
Middle Technical university, Institute of Medical Technology Al-Mansour, Iraq.
ABSTRACT
Local Binary Patterns (LBP) is a non-parametric descriptor whose purpose is to effectively summarize local
image configurations. It has generated increasing interest in many aspects including facial image analysis,
vision detection, facial expression analysis, demographic classification, etc. in recent years and has proven
useful in various applications. This paper presents a local binary pattern based face recognition (LBP)
technology using a Vector Support Machine (SVM). Combine the local characteristics of LBP with universal
characteristics so that the general picture characteristics are more robust. To reduce dimension and maximize
discrimination, super vector machines (SVM) are used. Screened and Evaluated (FAR), FARR and Accuracy
Score (Acc), not only on the Yale Face database but also on the expanded Yale Face Database B datasets,
the test results indicate that the approach is accurate and practical, and gives a recognition rate of 98 %.
Keywords: Face Classifaction, False Reject Rate ,Local Binary Pattern, False Accept Rate ,Support
Vector Machine.
Corresponding Author:
Seba Aziz Sahy
Middle Technical university
Institute of Medical Technology
Al-Mansour, Iraq
E-mail: saba.aziz@mtu.edu.iq
1. Introduction
Faces are significant in our social lives since they allow us to learn about people's personalities, genders, ages,
familiarity, and emotions. Humans recognize known faces more quickly and reliably than new faces, which is
especially obvious in difficult viewing conditions where novel face classification frequently fails [1]. The
development of biometric applications such as facial recognition has recently been a major priority in smart
cities. Furthermore, numerous physicists and engineers all over the world have worked to design highly effective
and powerful algorithms and procedures for these systems, which they now utilize in their daily lives. All types
of security systems must secure personal data. The most frequent type of identification is a password. Many
applications have begun to use a variety of biometric variables for the identification role because of the
development of information technology and authentication algorithms [1,2,3,4]. People can be identified based
on physiological or behavioral features thanks to these crucial variables. It also has several benefits, such as
requiring only one person to stand in front of the sensor and removing the need for multiple keys or secret codes.
Many biometric recognition systems, such as iris, fingerprint [5, and speech [6], are based on this principle, and
the face to this effect has recently been published. Human identification systems that are biologically oriented
are appealing because they are simple to use. The human face is made up of a variety of structures and features.
It has become one of the most extensively used biometric identification technologies in recent years [7,8,9] due
to its capabilities in a variety of applications and domains (surveillance, home security, border control, and so
on). Consumers can already use face recognition as a recognition (identifier) outside of their phones, for
example, at airports, sports stadiums, and concerts. Furthermore, because this technology does not require
human contact to operate, people can be identified merely based on the photos captured by the camera.
Furthermore, numerous biometric technologies developed for various types of investigations have great
identification accuracy. However, it will be interesting to develop new biometric facial recognition solutions to
satisfy the real-time restrictions. [9] Feature extraction and classification are the two primary stages of a face