CHAPTER II

REVIEW RELATED LITERATURE

Foreign Literature

Face recognition is gaining popularity as one of the biometrics methods for

an attendance system in an organization. Due to the pandemic, the usual face

recognition system needs to be modified to meet the current needs, whereby

facemask detection is necessary. The main objective of this paper is to

investigate and develop a real-time face recognition system for the attendance

system based on the current scenarios. The proposed framework consists face

detection, mask detection, face recognition, and attendance report generation

modules, The face and facemask detection performed using the haar cascade

classifier. Two techniques for face recognition are investigated, the eigenfaces

and local binary pattern histogram. The initial experimental results and

implementation at Kuching Community College show the effectiveness of the

system. For future work, an approach that can perform masked face recognition

will be investigated (Suhaimin, et al., 2021).

Using a machine learning approach, a number of algorithms for automatic

face identification of offenders depending on specified goals have recently been

developed. Various algorithm has been proposed for face detection such as

Eigenface using PCA (Principal Compound Analysis), Fisherface using Linear

Discriminative method, Local Binary Pattern, active appearance, 3is research.

The data augmentation is also done, which provides the better performance in

training. Haar cascade is used for extracting the features like eyes, nose length,
cheek, lips, etc. Initially using the web camera, the individual persons cropped

grayscale images are collected as database. Then the classifier trains the

images, the data augmentation is used when datasets of the person is not

enough. Using the web camera, the images are detected and recognized the

person and that information as message are sent to WhatsApp (Saravanan et al.,

2022).

In modern times, Security and surveillance in households have become

somewhat of an especially important necessity. Advancement in technology has

made it possible for everyone to access or break into different houses easily. The

main purpose of our project is to build an advanced surveillance system that can

be used to detect the different faces or any movement that may occur while in

the view of the surveillance camera. This system is also supported by an

application that has unique features to make it more user friendly for the users.

Not only is the user notified when an unauthorized entity is detected, the user is

also allowed to add different faces or objects that will be ignored during the

process of theft detection. This has been achieved using unsupervised machine

learning where a given set of data is compared with the actual live feed from the

surveillance camera to check for any anomalies in its surroundings. The Dataset

or the data used in the proposed system are a few images in the format of. JPEG

and. JPG which can be stored in the given location manually by the user or

through the application itself. The proposed model recognizes the images in any

of the available formats. The modules used in this system are powered by a

strong python module named Open CV. This module supports various face

7
recognition algorithms such as Haar Cascade, Eigen Faces, Fischer Faces,

Local Binary Pattern Histogram (LBPH), etc and this module is responsible for all

the image recognition, classification, and identification. The images extracted

from the dataset are real time Image frames obtained from the user webcam,

both are compared using the Face Recognition module in python which uses the

Regions for - Convolutional Neural Network Algorithm (R-CNN) and

Unsupervised learning approach to detect and differentiate between objects in

Real Time. This system also includes a message transmitting feature which

works with the help of the Simple Message Transfer Protocol (SMTP) module in

python. Whenever an unknown user is identified by the system an email is sent

to the admin or the user using the SMTP message transfer module which

registers the mail address of the user when the initial setup of the system takes

place. Hence a robust, secure and user-friendly device is developed that can

always keep your house theft free (Savitha et al.,2022).

Face Recognition is the most popular and trending technology in the

present era. It is an effective way to provide vision to a machine for better

interaction with humans. The way of living will be reflected if machines can read

our faces. The face recognition system will move the world in a new dimension. It

will be beneficial in many ways to find the identity and security. In this paper, a

face recognition system is proposed for advanced applications such as access

and security, payments, criminal identifications etc. The process of identification

will be based on face recognition which is further divided into three steps:

detection of face, extractions of the features and classification, and real time

8
recognition. Detection of face is recognized as the essential step of our system. It

is used to extract a face in a frame, which is based on the Viola-Jones object

detection algorithm that uses AdaBoost classifier with Haar and LBP features.

Local Binary Patterns (LBP) is utilized to extract the unique features of the face

like eyes, nose, and mouth in the feature extraction phase. The facial image is

correlated with the images available in the database for the classification. The

system is implemented in Python using OpenCV library. Kivy is used to create a

user interface and also to build executables for different platforms (Sharma,

2019).

Face recognition is one of the challenging problem in the Computer

Vision industry. Many algorithms have been developed to address the issue

of facial recognition during the last thirty years. Algorithms based on LDA,

PCA, ICA and Artificial Neural Networks have been used to try to address the

issue of face recognition. Facial recognition algorithms are affected by

illumination thus variation in lighting as well as pose variation. As a result,

hybrid methods have been developed which uses a combination of two

algorithms. Face Recognition has been greatly used to develop security

systems as well as surveillance systems to keep track fraud and criminal

activities. In this paper, the researcher used the LBPH (Local Binary

Patterns Histograms) algorithm to produce a prototype of a system that will

find missing people using facial recognition. The major objective of the research

is to determine the accuracy of the system as well as the recognition rate

(Muyambo, 2018).

9
Local Literature

At one of the most successful applications of image analysis and

understanding, face recognition has recently received significant attention,

especially during the past few years. Facial recognition technology (FRT) has

emerged as an attractive solution to address many contemporary needs for

identification and verification of identity claims. It brings together the promise of

other biometric systems, which attempt to tie identity to individually distinctive

features of the body, and the more familiar functionality of visual surveillance

systems. Face recognition technology may solve this problem since a face is

undeniably connected to its owner except in the case of identical twins. It's

nontransferable. The system can then compare scans to records stored in a

central or local database or ever on a smart card (Zarkasyi et al., 2020).

A large number of people around the world are suffering from visual

impairment which is a global health issue. These visually challenged people face

a great deal of difficulties in carrying out their day-to-day activities. Recognizing a

person is one of the major problems faced by them. This document represents a

face recognition system with auditory output which can be beneficial for visually

challenged people in recognizing known and unknown persons. Proposed face

recognition system is comprised of three main modules including dataset

creation, dataset training, and face recognition. Here, Haar Cascade Classifier is

used to detect face from a live video stream and then Local Binary Pattern

Histogram (LBPH) algorithm is applied to create the recognizer for face

recognition using OpenCV-Python library. This system can detect and recognize

10
multiple people and is also capable of recognizing from both front and side face.

The overall face recognition accuracy is about 93%. Apart from visually

challenged people, old people with Alzheimer's disease can also be benefited

using this system (Sarwar, et al., 2021).

Face recognition has been thought-provoking task in object detection,

digital image processing and pattern recognition. Face recognition plays a

significant role in real-time surveillance systems. In this paper, we present a

comprehensive overview of the state-of-the-art research work on face detection

and recognition. Furthermore, the performance analysis of various face

recognition approaches is discussed and conclude the paper with future research

direction. (Sharmila et al., 2019).

Providing security to the citizens is one of the most important and complex

tasks for the governments around the world which they have to deal with. Street

crimes and theft are the biggest threats for the citizens and their belonging. In

order to provide security, there is an urgent need of a system that is capable of

identifying the criminal in the crowded area. This paper proposes a facial

recognition system using Local Binary Patterns Histogram Face recognizer

mounted on drone technology. The facial recognition capability is a key feature

for a drone to have in order to find or identify the person within the crowd. With

the inception of drone technology in the proposed system, we can use it as a

surveillance drone as well through which it can cover more area as compared to

the stationary system. As soon as the system identifies the desired person, it

tags him and transmits the image along with the co-ordinates of the location to

11
the concerned authorities using mounted global positioning system. Proposed

system is capable of identifying the person with the accuracy of approximately

89.1% (Wang Li et al., 2020).

Automatic individual face recognition is the most challenging query from

the past decade in computer vision. However, the law enforcement agencies are

inadequate to identify and recognize any person through the video monitoring

cameras further efficiently; the blur conditions, illumination, resolution, and

lighting are still the major problems in face recognition. Our proposed system

operates better at the minimum low resolution of 35px to identify the human face

in various angles, side poses and tracking the face during human motion. We

have designed the dataset (LR500) for training and classification. This paper

employs the Local Binary Patterns Histogram (LBPH) algorithm architecture to

address the human face recognition in real time at the low level of resolution

(Ahmed, et al., 2018).

Foreign studies

Face recognition technology is an important research project in the field of

computer vision and pattern recognition, it can identify the identities and other

information according to the visual features of face image, having a very broad

prospects for development. It is widely used in authentication, criminal

investigation, video surveillance, robot intelligence and medical science and so

on. It has wide application value and commercial value. As a biological feature,

facial features have the characteristics of good, direct and convenient compared

with other biological features. Therefore, face recognition is more acceptable for

12
users. Over the years, many scholars have developed a variety of kinds of face

recognition algorithms, Local Binary Pattern Histogram (LBPH) Compared with

the other two algorithms, the LBPH algorithm can not only recognize the front

face, but also recognize the side face, which is more flexible. In order to enhance

the robustness of illumination changes, expression change and attitude

deflection, a LBPH algorithm based on pixel neighborhood gray median(MLBPH)

is proposed. The gray value of the pixel is replaced by the median value of its

neighborhood sampling valueˈand then creating the face database of our own,

extracting LBP feature and MLBP feature, and being trained in the face

database. After that, it is extracted the feature of testing images, established

block histogram, and compared with the database, and then printed the

corresponding name in face recognition frame. (Yu et al., 2021).

Face recognition (FR) in an unconstrained environment, such as low light,

illumination variations, and bad weather is very challenging and still needs

intensive further study. Previously, numerous experiments on FR in an

unconstrained environment have been assessed using Eigenface, Fisherface,

and Local binary pattern histogram (LBPH) algorithms. The result indicates that

LBPH FR is the optimal one compared to others due to its robustness in various

lighting conditions. However, no specific experiment has been conducted to

identify the best setting of four parameters of LBPH, radius, neighbors, grid, and

the threshold value, for FR techniques in terms of accuracy and computation

time. Additionally, the overall performance of LBPH in the unconstrained

environments are usually underestimated (Ahsan et al., 2020).

13
 One of the most significant and extensively studied local texture

descriptors is called Local Binary Patterns (LBP). In the studies, a

comprehensive analysis of the most renowned LBP related procedures is

required in order to make sense of them all. Descriptors have been created using

multistage convolutional neural networks (CNN) in deep learning. With low-

resolution pixels, this work presents an enhanced real-time facial identification

system that integrates posture, mood and resolution variations. We produced

training and classification datasets. Face detection and recognition is performed

using the different algorithm, which gets the face picture. With an updated

database, the training and recognition process will resume automatically. The

distance between a person and camera can be used for this facial recognition

technology to help security forces in system. A surveillance system for airports,

bus terminals and other public locations can also be installed to reduce the risk of

criminal activity. To lessen the possibility of criminal behaviour, a surveillance

system for airports, bus terminals and other public venues can be implemented

(Shukla et al., 2023).

In the workplace of today, workplace security is a significant concern.

Facial recognition-based security solutions are offered by computer vision and its

applications to address the security issues. Humans perform facial recognition on

a daily basis relatively readily. The creation of a trustworthy facial recognition

system is the aim of this paper. An instant face recognition-based security

system for homes and workplaces is described in this article. The Local Binary

Pattern Histogram (LBPH) algorithm was used in its development. For workplace

14
security, a Facial Recognition model based on LBPH has been created and

tested. During the testing of recognition algorithms, critical characteristics such

as illumination, variations in human face features, poses, and angles have been

chosen. This model exceeded 85% accuracy while successfully navigating the

two situations. This type of system can be utilized for video monitoring at airports,

busy areas, and on the streets. The outcome reveals that LBPH FR is superior to

Eigenface and Fisherface because of its durability in a variety of lighting

conditions (Srivastav et al., 2022).

Internet of Things (IoT) with deep learning (DL) is drastically growing and

plays a significant role in many applications, including medical and healthcare

systems. It can help users in this field get an advantage in terms of enhanced

touchless authentication, especially in spreading infectious diseases like

coronavirus disease 2019 (COVID-19). Even though there is a number of

available security systems, they suffer from one or more of issues, such as

identity fraud, loss of keys and passwords, or spreading diseases through touch

authentication tools. To overcome these issues, IoT-based intelligent control

medical authentication systems using DL models are proposed to enhance the

security factor of medical and healthcare places effectively. This work applies IoT

with DL models to recognize human faces for authentication in smart control

medical systems. We use Raspberry Pi (RPi) because it has low cost and acts as

the main controller in this system (Hussain et al., 2022).

15
Local Studies

This study shows how useful and feasible in facial recognition a triangular

feature of the face using the left and right Lateral Canthus, Nasal Bridge, and

Apex of the Nose. These features are sometimes overlooked by traditional facial

recognition programs. This paper explores a different approach using a triangle

method for facial recognition utilizing DLIB and OpenCV to create the machine

learning model. It has been found that the approach can be viable only with a

certain distance of the camera to the face. With a 92% accuracy of the machine

learning model, the research has concluded that the approach is feasible but has

a constraint on the setup (Sanchez et al., 2020).

The Manila City Government just recently implemented a city ordinance of

strict implantation of curfew for minors. Upon conducting interviews, the

researchers found out that the system of implementation of curfew uses

manpower and barangay patrol roaming around the barangay. This study aims to

develop a curfew monitoring system using Image Processing with notifying

features via SMS. LBPH (or Local Binary Pattern Histogram) algorithm is

implemented in the study. The system was successful in recognizing faces that

are registered to the system. The challenge that the researchers encountered

was the range of facial recognition is limited. People that are far away cannot be

recognized by the system. Also, that the face should be facing the camera.

Having any angle with the camera will make the % confidence of the recognition

lower. The system has great recognition with the face facing directly at the

camera with 15 degrees tolerance (Balbin et al., 2021).

16
 Adaptive facial recognition includes the features of artificial intelligence

(AI) technology, internet of things (IoT) devices, and wireless fidelity (Wi-Fi)

connection. The application of Artificial Intelligence was used to detect faces from

the captured images. Using video image to extract features from the face, Local

Binary Pattern Histogram (LBPH) algorithm was used. The ideal distance

between the subject and the webcam must be 30 cm for minimum percent error.

The study proposes a designed face recognition system of surveillance cameras

that adapts through the changes of the features of the person by re-training the

AI by saving various images of it. This utilizes the component Raspberry Pi 4

where the local binary pattern histogram is applied. Based on the results, the

proposed method was able to produce an overall detection accuracy of 91.72%

and an average processing time of 1.4 seconds. The output shows very

promising results for face detection devices in the field of face recognition

monitoring system (Garcia et al, 2021).

Animal identification allows producers to keep records on the most

important information such as breed, date of birth, and gender. Plastic tags on

water buffaloes (Bubalus Bubalis) are prone to damage and in order to be read,

they should be restrained. The main objective of the study is to create a portable

device that can identify the buffalo by taking its facial image. This study shows

that with the use of Linear Discrimant Analysis (LDA), the water buffaloes can be

identified by just taking a photo of its face for training images and testing images.

In comparison with various algorithms used for the identification of water

buffaloes, Local Binary Patterns Histograms (LBPH) shows more accurate

17
results compared to other algorithms such as Principal Component Analysis

(PCA), Linear Discriminant Analysis with Support Vector Machine (LDA+SVM)

and LDA alone. The output of the simulated training images and testing images

show favourable results indicating effectiveness of the study (Cruz et al., 2019).

While network technology is convenient for our daily life, the problems that

are exposed are also endless. The most important thing for everyone is

information security. In order to improve the security level of network information

and identify and detect faces, the method used in this paper has improved

compared with the traditional AdaBoost method and skin color method. AdaBoost

detection is performed on the image, which reduces the probability of false

detection. The experiment compares the experimental results of the AdaBoost

method, the skin color method and the skin color + AdaBoost method. All

operations in the KPCA and KFDA algorithms are performed by the inner product

kernel function defined in the original space, and no specific non-linear mapping

function is involved. The full name of KPCA is kernel principal component

analysis (Sun et al., 2022).

18