Indian Journal of Artificial Intelligence and Neural Networking (IJAINN)
ISSN: 2582-7626 (Online), Volume-1 Issue-3, June 2021
12
Retrieval Number: 100.1/ijainn.B1027021221
DOI:10.35940/ijainn.B1027.061321
Journal Website: www.ijainn.latticescipub.com
Published By:
Lattice Science Publication
© Copyright: All rights reserved.
A Hybrid Enhanced Real-Time Face Recognition
Model using Machine Learning Method with
Dimension Reduction
Jaya Kumari, Kailash Patidar, Gourav Saxena, Rishi Kushwaha
Abstract:Face recognition techniques play a crucial role in
numerous disciplines of data security, verification, and
authentication. The face recognition algorithm selects a face
attribute from an image datasets. Recognize identification is an
authentication device for verification as well as validation having
both data analysis and feasible significance. The face-
recognizing centered authentication framework can further be
considered an AI technology implementation for instantly
identifying a particular image. In this research, we are
presenting a hybrid face recognition model (HFRM) using
machine learning methods with “Speed Up Robust Features”
(SURF), “scale-invariant feature transform” (SIFT), Locality
Preserving Projections (LPP) &Principal component
analysis (PCA) method. In the proposed HFRM model SURF
method mainly detects the local feature efficiently. SIFT method
mainly utilizes to detect the local features and recognize them.
LPP retains the local framework of facial feature area which is
generally quite meaningful than on the sequence kept by a
'principal component analysis (PCA) as well as “linear
discriminate analysis” (LDA). The proposed HFRM method is
compared with the existing (H. Zaaraoui et al., 2020) method and
the experimental result clearly shows the outstanding
performance in terms of detection rate and accuracy % over
existing methods.
Keyword: Speed up Robust Features, Hybrid Face
Recognition Model, Linear Discriminate Analysis, PCA, LPP
I. INTRODUCTION
In the last decade, it can be observed that many
algorithms were developed in image processing for face
recognition and face detection but there was no algorithm
for detecting a position in an image. The position detection
in the controlled environment can be used in many
environments where the positions are fixed.
Manuscript received on April 03, 2021.
Revised Manuscript received on May 21, 2021.
Manuscript published on June 10, 2021.
* Correspondence Author
Jaya Kumari*, M.Tech Scholar, Department of Computer Science,
School of Engineering, Sri Satya Sai University of Technology & Medical
Sciences, Sehore, Madhya Pradesh, India. Email: Pathak.jayak@gmail.com
Kailash Patidar, Assistant Professor, Department of Computer
Science, School of Engineering, Sri Satya Sai University of Technology &
Medical Sciences, Sehore, Madhya Pradesh, India. Email:
kailsashpatidar123@gmail.com
Mr. Gourav Saxena, Assistant Professor, Department of Computer
Science, School of Engineering, Sri Satya Sai University of Technology &
Medical Sciences, Sehore, Madhya Pradesh, India. Email:
gauravsss1999@gmail.com
Mr. Rishi Kushwaha, Assistant Professor, Department of Computer
Science, School of Engineering, Sri Satya Sai University of Technology &
Medical Sciences, Sehore, Madhya Pradesh, India. Email:
rishisinghkushwah@gmail.com
© The Authors. Published by Lattice Science Publication (LSP). This is an
open access article under the CC BY-NC-ND license
(http://creativecommons.org/licenses/by-nc-nd/4.0/ )
The face is a particularly deformable object, and facial
expressions are available in an extensive form of viable
configurations. Time-various adjustments encompass boom
and elimination of facial hair, wrinkles, and sagging of the
pores and skin resulting from growing older and change in
pores and skin color because of publicity to sunlight.
Artifact-related modifications encompass cuts, scrapes, and
bandages from injuries and style-associated problems like
makeup, rings, and piercings. It needs to be pretty clear that
the human face is a whole lot extra tough to model and
recognize than maximum industrial elements [1,2].
The face recognition [3,4] procedure is prompted
through numerous elements consisting of a form,
reflectance, pose, occlusion, and illumination. A human face
is an incredibly complex object with functions that can vary
over the years, every so often very hastily. In this research,
we are presenting a hybrid face recognition model (HFRM)
using machine learning methods. This complete paper is
organized in various sections which cover face recognition,
application and challenges, related work, proposed HFRM
model, simulation details, experimental results and finally
covers conclusion and future work.
II. FACE RECOGNITION, APPLICATION, AND
CHALLENGES
Face detection is a technology that determines the sizes
and locations of human faces in digital images. It recognizes
faces and ignores anything else, such as trees, bodies, and
buildings. Face detection might be recognized as a more
general instance of face confinement. It is the center of all
facial analysis, e.g., face localization, and face recognition,
face authentication, facial feature detection, face tracking,
and facial expression recognition. Additionally, it is
essential strategies for all different requisitions, for example,
feature conferencing, substance-based picture recovery, and
adroit human-machine cooperation (HCI) (S. Bhatia et al.,
2019).
2.1Types of face recognition methods-Face recognition
and detection have been one of the most studied topics in
computer vision literature. It uses the following methods (S.
S. Ali, et al., 2018). Table 1.1 is showing the types of
recognition methods.