PAMANTASAN NG LUNGSOD NG MUNTINLUPA

Development of an Attendance Monitoring System with Facial

Recognition using Raspberry Pi for Ang Dating Daan Coordinating
Center Alabang

A Capstone Project Presented to the Faculty of College of Information Technology

and Computer Studies
Pamantasan ng Lungsod ng Muntinlupa

In Partial Fulfillment of the Requirements for the Degree Bachelor of Science

Information Technology

AVENSON P. TALADTAD
JOMAR BUENO
VELMORE L. BULAKLAK

November 2019
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
TABLE OF CONTENT
Title Page
Approval Sheet
Acknowledgement
Executive Summary
Table of Content
List of Figures
List of Tables

CHAPTER
1. INTRODUCTION
Project Context
Purpose and Description
Objective of the Study
Scope and Limitation

2. REVIEW OF THE RELATED LITERATURE AND STUDIES

Technical Background
Related Literature
Related Studies
Definition of Terms

3. METHODOLOGY
Requirement Analysis
Requirement Documentation
Design of Software, Systems, Product and/or Processes
Development and Testing
Implementation Plan

4. RESULTS AND DISCUSSIONS

Project Description
Project Structure
Project Capabilities and Limitation
Project Evaluation

5. SUMMARY OF FINDINGS, CONCLUSION AND

RECOMMENDATION
Summary of Findings
Conclusion
Recommendation
References
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA

CHAPTER 1
INTRODUCTION
Project Context

Face recognition is a task so common to humans, that the individual does not

even notice the extensive number of times it is performed everyday. Although

research in automated face recognition has been conducted since the 1960’s, it has

only recently caught the attention of the scientific community. Many face analysis

and face modeling techniques have progressed significantly in the last decade.

However, the reliability of face recognition schemes still poses great challenge to the

scientific community.

Human identification is a basic societal requirement for proper functioning of

a nation. By recognizing a face, you could easily detect a stranger or identify a

potential breach of security. In todays larger, more complex society it isn’t that

simple with all the growing electronic interactions. So it becomes even more

important to have an electronic verification of a person’s identity. Until recently,

electronic verification was done either based on something the person had in their

possession like an ID card, or on something they knew, like a password.

The major problem is that these forms of electronic identification are not very

secure as they can be faked by hackers, maliciously given away, stolen or even lost.

Therefore, the ultimate form of electronic verification of a person’s identity is

biometrics. That is using a physical attribute of a person to make an affirmative

identification. This is because such attributes like finger print, Iris or face of a person
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
cannot be lost, given away, stolen or forged by hackers. Falsification of identity

cards or intrusion of physical and virtual areas by cracking alphanumerical passwords

appears frequently in the media.

These problems of modern society have triggered a real necessity for reliable,

user-friendly and widely acceptable control mechanisms for the identification and

verification of the individual. Biometric authentication and their template security are

increasing day by day over the past decade with challenging requirement in

Automated Secured Personal Authentication System. The reason behind on this

demand for the replacement of old fashioned automatic personal identification tools

by new one. The old-fashioned automatic personal identification tools uses traditional

approaches such as Personal Identification Number (PIN), Login Id, ID card,

password etc. to verify the cognizance of a person, are no longer considered as

credible adequate to gratify the security Concern for person identification system.

A biometric scheme delivers automatic recognition of a person depending on

some particular trait. Biometric Identification Systems are widely used for unique

identification of humans mainly for verification and identification Biometrics is used

as a form of identity access management and access control. So the use of biometrics

in the member attendance management system is a secure approach.

The Ang Dating Daan Locale of Alabang was started in 1998 with

approximate 100 members during that time they only manually taken the attendance

each of the members before the church service. It was easy to monitored the

attendance and determine the member who was been inactive in the church. The

workers would review the attendance and determined the inactive members. At the
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
end of the month the workers of the locale will visit the inactive member and remind

them about their actions. Over the years, the population of the members of Ang

Dating Daan increased.

Due to its increasing population the manual attendance as well as monitoring

the inactive members becomes a challenge for the worker of Ang Dating Daan. In

2013 the automated Attendance monitoring system via RFID using a bar code with

ID was introduce to the locale of Alabang the member who has an ID from the

Central (the main office of their Church) were able to perform their attendance

automatically with ease but for the (provisionary) member were still using the manual

system as well as the visitor from the other locale. In manual process, both the

(provisionary) member and the visitor receive a piece of paper called "Katibayan" or

proof of attendance which will be use in a certain purposes.

The RFID-based attendance system has been a great solution to cater the

growing population of members of Ang Dating Daan locale of Alabang. As of

January 2019 there were about 600+ active members in the church. The automate

Attendance monitoring became a necessity to the institution amidst to its growing

population. Since then, the RFID-based attendance system has been used in locale of

alabang the institution relied on it. Over the time due to poor maintenance, the system

has slowed down and has gone crazy. In 2017, the programmer who took care of the

system decided to leave that results permanently malfunctioning of the system.

Unfortunately, the RFID-based Attendance system is often unusable because

it usually does not work. For example when the barcode in a member's id is so

obscured that it cannot be read by the scanner or sensor the system can’t as well
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
perform attendance monitoring for new members who does not have an ID yet from

the Central. The system does not have a user interface that can view report and sorted

it the way they need it. The workers had their hard times in retrieving and monitoring

each member's attendance, which is why the workers in the locale of the Alabang

have reverted to manual retrieval of members records and Attendance monitoring

more often.

To overcome the problems in the existing attendance system the researchers

develop Biometric based attendance system over RFID-based attendance system.

There are many solutions to automate the attendance management system like thumb

based system, simple computerized attendance system, Iris scanner, but all these

systems have limitations overwork and security point of view. The develop system

uses the basic idea of image processing which is used in many security applications

like banks, airports, Intelligence agencies etc.

The develop system which uses Facial recognition to capture and monitor

member's attendance. The system is able to monitor new member’s attendance as it

requires no physical ID. The researcher develops a system with a user-friendly

dashboard where a worker can view, modify, search and delete a member's data. The

system has an additional feature whereby workers can give reminders to inactive

members and send notifications using SMS technology.

Purpose and Description

The develop system will uses two step mechanisms. The first method will

detect the face from the real time environment and followed by the face recognition.

The first method is achieved by using Camera which is connected to Raspberry pi. It
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
will captures the images of the members, Then the detected face is compared with the

stored data of every member. The member database is collected and stored into the pi

at the initial stage. The database includes name of the members, their images and

registered number. The raspberry pi is fixed at the front side of facility in such a way

that we can capture entire room. Thus with the help of this system, time will be saved

and it is so convenient to record attendance. We can take attendance on any time

without any human Intervention.

The develop system in which the member data is created in the organization

database, the photo will be uploaded into the database as well. First, it will detect the

faces from the live video streaming from the camera. Using suitable face recognition

algorithms, the face matching is done with the member when he enters into the

institution from the live video captured by the cameras. This step acts as first layer of

security for the sensitive places. If match of the face does not happen then alarm gets

triggered and security personnel will take action.

The develop system benefits the following:

Members the Automated Attendance Monitoring System using raspberry pi

will be able to cater both new and old member of the organization to improve the

process performing attendance at ease.

Workers the develop system will be able to help the workers of locale of

Alabang to monitor the attendance as well as retrieving members data and making

reports.

Institution the develop system will be able to help the institution of Ang

dating Daan locale of alabang improve their process and services.

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
Researcher the study will be able to help the researcher to enhance their

knowledge in programming as well as project management skills.

Future Researcher this study will be able to help the future researcher as a

basis and guide in their future related projects.

Objective of The Study

General Objectives

The General objectives of this research study is to design an effective and

secure technique for personal authentication using facial recognition and also

evaluate the performance of the designed framework by comparing the performance

of existing Attendance monitoring system. The develop system will acquire

individual attendance by means of facial-recognition to secure data accuracy of the

attendance.

Specific Objectives

1. To design the System using the following features:

a. Creating a database that contains attendance information of the

members.

b. This automated system can perform CRUDE operations.

c. This automated system will capture live feed from camera to record

attendance times.

d. This automated system will link the information captured by the feed

to the database for accuracy results.

e. This automated system will send notification thru SMS notification.

f. This automated system will produce reports for monitoring purposes.

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
2. To develop a system using Python programming and SQLite3 as back end for

data base design and Django framework as front end.

3. To test the functionality of the system using the Test Cases method, and

4. To evaluate the performance of the system using ISO/IEC 25010-2011

software characteristics.

5. To implement the develop Automated Attendance Monitoring system using

raspberry pi to the Ang Dating Daan locale of Alabang.

Scope And Limitation

The Scope of this system is to solve the issues encountered in the old

attendance system while reproducing a brand new innovative smart system that can

provide convenience to the institution. In this project, a smart device will be develop

which is capable of recognizing the identity of each individuals and eventually record

down the data into a database system. Apart from that, a GIU will be developed to

provide visual access to the information. The design system comprising of two

modules, the first module (face detector) is a Hardware component, which is

basically a camera application that will captures member faces and stores them in a

file using computer vision face detection algorithms.

The second module is a desktop application that does face recognition. It

captured images (face marks the member register and then stores the results in a

database for future analysis). The system is able to send notification using SMS

technology. The system are capable of creating, modify user’s/member’s data. It also

has a capability of producing report.

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
The system is only limited to Attendance monitoring of Dating Daan Alabang

locale only. The database of the attendance management system can hold up to 5000

individual’s information. The facial recognition process can only be done for 4

people at a time. The workers are the only personnel allowed to add, modify and

delete member’s data. The system will not be able to detect faces with barriers like

hat, shades, scarf etc.

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA

CHAPTER 2
REVIEW OF THE RELATED LITERATURE AND STUDIES

Technical Background

The Concept of image processing through python OpenCV platform has been

used for human identification through face detection. Human Identification means to

recognize a particular people through his unique structure like fingerprint, palm, and

iris and face detection. SQLite3 is a relational database management system

(RDBMS) contained in a C library. In contrast to many other database management

systems for Raspberry PI; through this a user data has been stored in a particular

sequence and can be manipulated with Detection Window where a current image of

user has been displayed.

This mechanism is based on three steps, for the first we need to take dataset of

each person about 20 samples where an algorithm of face detection face.xml file is

used and is based on OpenCV. The second step of human identification is trainer,

which means we need to train our system and is converted that dataset into its

corresponding .YML file format. This YML file has been used on detector script and

is detected the respective face of user in real time when we run this detector file.

Through this detector window we can see real time picture along with corresponding

user information which has been linked with database and for an unknown person the

system said an unauthorized person.

Camera is connected to the raspberry pi camera slot. Camera captures the

images of the member who are present. Raspberry pi takes those images as input

images and compares the input images with the existing image. This happens due to
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
importing the open CV packages at the initial stage of the development of the

system. Workers track the attendance of the members periodically or whenever

required by the administration and find the result. The result is displayed on the

monitor screen which is connected to the raspberry pi through the Ethernet cable or

HDMI to VGA converter.

The researcher Develop a dashboard that use jQuery and Bootstrap as front

end of the system to help the developer in creating a more beautiful and immersive

user friendly UI design, jQuery's syntax is designed to make it easier to navigate a

document, select DOM elements, create animations, handle events, and develop Ajax

applications. JQuery also provides capabilities for developers to create plug-ins on

top of the JavaScript library. This enables developers to create abstractions for low-

level interaction and animation, advanced effects and high-level, Themeable widgets.

The modular approach to the jQuery library allows the creation of powerful dynamic

web pages and Web applications.

The researchers use Django as framework as back-end to add more security

and helps developers avoid many common security mistakes. The framework has

templates, libraries, and APIS which work together. In general, applications

developed using Django can be upgraded with minimal cost, changes, and additions

and it make a lot of web development easier. Django framework is widely used as it

is free and open-source developed and maintained by a large community of

developers. It means we can find answers to the problems easily using Google.
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
Related Literature

In the author proposed that different types of face detection for detecting faces

in different pose .Detecting face in different pattern based on techniques. Basic

pattern for detecting face is nose, eyes, hair, ears and some time it based on tone of

skin. Face detection is detecting face based on location of face and presences of face

in images .Different types of detecting the face techniques they are Ada-Boost

Algorithm for Face Detection, Viola Jones Face Detection Algorithm, SMQT

Features and SNOW Classifier Method, Local Binary Pattern (LBP). Each has

advantages and disadvantages discussed in that paper. [1]

The author proposed that recognition face using hog features and pca

algorithms. By applying recognition algorithm to cropped faces images from that we

get similarity b/w taken image and database image. [2]

The author shows that face recognition of facial of different person or student

.from recognition attendances is uploading to database using face detection and

recognition of student or workers. From this manual work is decrease by human and

automatically attendance system based on faces process done. [3]

The author proposed that capturing the images from camera or cc camera and

applying techniques face detection and recognition can decrease the manual work

from human and increase the security safety, taking the decision from this recognition

result. The complete system is implemented in MATLAB. Attendance system shows

the use of facial recognition techniques for the purpose of student attendance and for

the further process this record of student can be used in exam related issues. [4]

The author introduces a Near Field Communication (NFC) supported collage

attendance system for college students. In the most of collages lecturer take
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
attendance by calling out the names and surnames of students and then marking them

or pass the attendance sheet to students and asking students to sign in attendance sheet.

This both practices have their drawbacks. In first case if strength of students is more,

checking this entire student by name and surname might take about several minutes.

In second case if student is absent then friends of absent students may write down

their name and surnames.

These practices place college institutions at considerable disadvantages when

it comes to taking attendance. To come out from all these issues we put NFC tag into

service. Each tag has a unique ID, precluding the duplication of a tag. These NFC tag

are given to students when they registered in college. When student enter in class

rooms and touch or move these tag on lecturer mobile phone, NFC readers program

will read these tags, identify the students from the irrespective NFC tag and embedded

camera will capture the face of particular student then application send all the data to

college server and in server side validation program will check the data for validation

(compare new data with previous data which was already store in database) if valid

data found then program will update the database as marking attendance otherwise

mark student is absent.[5]

Introduce Machine Learning and demonstrate the application by using

Machine Learning algorithm, it is possible to train the machine to recognize facial

emotion without using hardcoded arguments. The program is not perfect, mainly due

to the size of the dataset provided (relatively small) and the error of SVM. To improve

the program, more data need to be provided and classified, which will increase

accuracy and performance of the program. Other algorithms could also be tested to

see which classification methods work best with the dataset provided.
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
The program just represents a tiny fraction in the Machine Learning field,

what its capability is. In the near future, Machine Learning will be one of the most

important fields in Computer Science. [6]

The author aims toward another successful implementation of Attendance

system using face detection and recognition. Manually taking attendance by teachers

because a lot of manipulation and a lot of confusion at times the automated system for

attendance designed by us prevent the extra proxies and manipulation of the data. It

also saves the time spent on counting the students and taking attendance, which in

turn can be used for betterment of students. Our Attendance system compromises of

four steps i.e. creating a database, taking a group photo of class, face segmentation,

matching the face with the database.[7]

The author’s goal is to explore the feasibility of implementing Raspberry Pi

based face recognition system using conventional face detection. This paper aims at

taking face recognition to a level in which the system can replace the use of

passwords and RF I-Cards for access to high security systems and buildings. With the

use of the Raspberry Pi kit, we aim at making the system cost effective and easy to

use, with high performance. This paper details the design and development of IOT

based security surveillance system in buildings using Raspberry Pi single board with

Wi-Fi network connectivity.

Upon detecting the face, the controller enables the camera for capturing the

event, alerts the user by placing the live video of that event on webpage that is

displayed in android mobile. [8]

Digital Image Processing is the processing of images which are digital in

nature by a digital computer. Digital image processing techniques are motivated by

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
three major applications mainly: Improvement of pictorial information for human

perception. Image processing for autonomous machine application. Efficient storage

and transmission[9].

This application employs methods capable of enhancing pictorial information

for human interpretation and analysis. Typical applications include; noise filtering,

content enhancements mainly contrast enhancement or deblurring and remote sensing.

In this, the interest is on the procedures for extraction of image information suitable

for computer processing. Typical applications include; Industrial machine vision for

product assembly and inspection. Automated target detection and tracking. Finger

print recognition. Machine processing of aerial and satellite imagery for weather

prediction and crop assessment. Facial detection and recognition falls within the

machine vision application of digital image processing [10].

Related Studies

A survey on facial feature extraction techniques for automatic face annotation,

Automatic face annotation is playing vital role in multimedia information. Automatic

face annotation is method to identify human faces from image and assign appropriate

human name. Face detection and face recognition are essential tasks in face

annotation. An author also discusses the phases of the automatic face annotation and

surveyed various techniques of facial feature extraction. [11]

Face Detection based ATM Security System using Embedded Linux

Platform. The system is implemented on the credit card size Raspberry Pi board with

extended capability of open source Computer Vision (OpenCV) software which is

used for Image processing operation. This technique is also based on OTP (one time

password) for establishing a high security for ATM. In an unauthorized condition

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
ATM door has been locked and it’s only when the OTP password is entered my

watchman. [12]

Face Identification System in Video. An author proposed CIE-Luv color

space, facial feature extraction and variance estimation. It can be applied in face

recognition systems such as video surveillance, human computer interfaces, image

database management and smart home applications. The experimental results

demonstrate the effectiveness of this system and its ability to recognize a variety of

different faces in spite of different pose, expression, zooming and illumination

conditions. [13]

Human Character Recognition Application Based on Facial Feature Using

Face Detection, This System can detect the human fundamental personality for the

same input image data with the training data and one way to know the human

fundamental personality is based on test, and one kind of test is Graph test

(handwriting test). In this study has been conducted detection of the human

fundamental personality using combination of some face features: the eyes, lips, and

nose (without test). Those features are obtained from facial image. [14]

Human Detector and Counter Using Raspberry Pi Microcontroller, This has

been developed with an application of histogram of oriented gradients (HOG) feature

descriptor using the OpenCV library coded with the High-level programming

language Python, booted with the help of Raspberry Pi microcontroller fitted with a

RaspiCam to capture moving images of objects passing under it has been

demonstrated. PIR motion sensor has been used to detect motion and a pi camera can

operated when there is a condition of motion detected. [15]

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
Human face detection algorithm via Haar cascade classifier combined with

three additional classifiers. Author has been use Haar cascade algorithm combined

with three additional weak classifiers based on skin hue histogram matching, eyes

detection and mouth detection. [16]

A system for Human face detection from images, based on skin color, Face

detection is necessary in many applications, like those for face recognition, face

tracking in video sequences, gender classification, biometric identification, Human

Computer Interaction systems, and others. [17]

Iris Movement Based Wheel Chair Control Using Raspberry Pi - A State of

Art. This wheel chair is highly applicable to disable person to execute their regular

task. This system has been designed using Raspberry Pi and IR Camera Module.

OpenCV will be used for image processing and Python is used for programming the

Raspberry Pi. [18]

A system using raspberry pi the current project can be modified by an

Infrared camera interfacing it can be used in Smart Surveillance Monitoring security

system which any type of public security is using Living body detection or spying,

Also it can be used in Attendance system of the class, Real time face detection and

face detection from specific images, i.e. object recognition, was carried out. The

analysis revealed that the present system shows excellent performance efficiency. [19]

Face detection and recognition system. This system detects faces of

individuals on the basis of intensities of pixels in the snap shots. The ARM Processor

module is used for displaying Number of Presenters and the people present. The

camera will be connected to the ARM. The student or employees database is collected.

The database includes name of the students/employees, there images. This webcam
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
module will be installed at the front side of class in such a way that it can capture

entire class or in front of a main office door. Thus with the help of this system, time

will be saved and it will be very much convenient to record attendance. [20]

Related System

Figure 1: Face recognition based attendance management system using raspberry

pi2 using Eigen faces algorithm

This figure show using face detection and recognition technology, a time

period is settled for taking the attendance and after completion of time period

attendance will directly stores into storage device mechanically without any human

intervention. A message will send to absent student parent mobile using GSM

technology. This attendance will be uploaded into web server using Ethernet. This

raspberry pi 2 module is used in this system to achieve high speed of operation.

Camera is interfaced to one USB port of raspberry pi 2. Eigen faces algorithm is used

for face detection and recognition technology.

Eigen faces algorithm is less time taken and high effective than other

algorithms like viola-Jones algorithm etc. the attendance will directly stores in storage

device like pen drive that is connected to one of the USB port of raspberry pi 2 [22].
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA

Figure 2: Image Processing Based Student Attendance System using Raspberry PI

The figure 2 shows that Image processing based Student Attendance System

using Raspberry pi using Open CV tool as software for image processing and

attendance is provided to the students, The system can track the attendance of the

students by using the language python and Open CV software, which is very easy to

install and is open source software and can be used in real time application in a quick

manner. The project has shown the tracking of the students in the class by using

camera in the system. This proposed system reduces the possibilities of proxy

attendance of the students, who were not present in the class and reduces the time. [23]
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA

Figure 3: Efficient human Identification through face detection

Figure 3 shows efficient human Identification through face detection has been

carried out with the use of PHPmyadmin and SQLite Studio database for storing

relevant information. The performance of the system is based on three steps which are

datasets, trainer and detector python script. An algorithm that has been used for image

processing is OpenCV and especially for face detection “Haar cascade frontal face”

has been used. As we talk about future modification of this project, it will be used in

high security system and face detection based attendance system. Also we can

develop projects based on Image Processing, Neural Network and Artificial

Intelligence (AI). [24]

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA

Figure 4: Attendance based on facial recognition

The figure 4 show the graphic interface and capturing the images from camera

or cc camera and applying techniques face detection and recognition can decrease the

manual work from human and increase the security safety, taking the decision from

this recognition result. In this system implemented an attendance system for a lecture,

section or laboratory by which lecturer or teaching assistant and record student’s

attendance. [25]
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
DEFINITION OF TERMS

Technical terms

Biometrics - An application of statistical analysis to biological data.

Python - is an interpreter, high-level, general-purpose programming language.

Created by Guido van Rossum and first released in 1991, Python's design

philosophy emphasizes code readability with its notable use of significant

whitespace.

OpenCV - is a library of programming functions mainly aimed at real-time computer

vision. Originally developed by Intel, it was later supported by Willow

Garage then Itseez. The library is cross-platform and free for use under the

open-source BSD license.

Raspberry Pi 3 Model B - is a tiny credit card size computer. Just add a keyboard,

mouse, display, power supply, micro SD card with installed Linux

Distribution and you'll have a fully fledged computer that can run applications

from word processors and spreadsheets to games.

YAML - stands for "YAML Ain't Markup Language" and it is used extensively in

Grav for its configuration files, blueprints, and also in page settings. YAML is

to configuration what markdown is to markup. It's basically a human-readable

structured data format. ... At its core, a YAML file is used to describe data.

SQLite3 - is compact free databases you can use easily create and use a database.
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
Facial Recognition System - is a technology capable of identifying or verifying a

person from a digital image or a video frame from a video source.

Intrusion - An act to compromise a computer system by breaking the security of

such a system or causing it to enter into an insecure state. The act of

intruding—or gaining unauthorized access to a system—typically leaves

traces that can be discovered by intrusion.

Algorithm - In mathematics and computer science, an algorithm is an unambiguous

specification of how to solve a class of problems. Algorithms can perform

calculation, data processing, automated reasoning, and other tasks.

GUI - graphical user interface is a form of user interface that allows users to interact

with electronic devices through graphical icons and visual indicators such as

secondary notation, instead of text-based user interfaces, typed command

labels or text navigation.

Database - is an organized collection of data, generally stored and accessed

electronically from a computer system. Where databases are more complex

they are often developed using formal design and modeling techniques.

Python library - is a collection of functions and methods that allows you to perform

many actions without writing your code. For example, the Python imaging

library (PIL).is one of the core libraries for image manipulation in Python.

Worker- a personnel who are facilitating the Institution They are the one who

handled the attendance Systems and other process and services related to the

institution.
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
Operational Terms

Image Training - Facial image comparison practitioners compare images of

unfamiliar faces and decide whether or not they show the same person.

Image Detection - This information is then used to identify distinctive features on

the surface of a face, such as the contour of the eye sockets, nose, and chin.

One advantage of 3D face recognition is that it is not affected by changes in

lighting like other techniques.

Image cropping (Frame a Face) - is a state-of-the-art application that uses facial

recognition software to crop large batches of images. Load hundreds of

images, set the cropping parameters and let your computer do the work.

Frame a Face's sophisticated facial recognition library will locate the

subject's.

Attendance Monitoring - is used to monitor the attendance and movement of

employees within their working hours and to prepare materials for processing

wages.
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
CHAPTER 3
METHODOLOGY

This chapter provides an outline of the research methodology that will answer

the questions of the study and contains the research design, validation of data, and

instruments used in collecting data. This is also contains charts and templates that

show the system works according to its project plan.

Requirement Analysis

This topic discussed the requirements needed for developing the project. This

part also describes the processes in the system.

Figure 5: Data Flow Diagram of Existing RFID-Based Attendance Monitoring

System Context level 0

This figure shows the process of the existing RFID based Attendance

monitoring system. It shows that the worker manages the system and provides report.
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
The Members enters information and perform attendance using their barcode Id. The

system authenticates the members ID and save the attendance log in the database.

Figure 6: Data Flow Diagram of Existing RFID-Based Attendance Monitoring

System Context level 1

This figure shows the member’s registration or enrollment to the system. The

worker register’s the member’s data to the system. The data are saved in the database.

It also shows how the attendance process are done, the user tap their Barcode ID, the

system will authenticate it by matching the id in the database and the entered id if

successfully match the system will mark the attendance and save it to the attendance

table.
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
Requirement Documentation

Requirement documentation explains why a project is needed, puts the project

in context, and describes what the finished project will be like. Requirement includes

description of system properties, specification of how the system should work, and

constraints placed upon the development process. Generally, requirements are

statements of what a system should do rather than how it should do it. Requirements

come from end users, and sometimes from developers. Requirements documents

usually include user, system and interface requirements; other classes of requirements

are included as needed.

Figure 7: Data Flow Diagram of Attendance Monitoring System Using Facial

Recognition Context level 0

The figures show the contextual level of the developed Attendance monitoring

system using facial recognition. The worker manages the system and the member’s

perform their attendance using facial recognition. The system sends SMS notification

for the inactive members.

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA

Figure 8: Data Flow Diagram of Attendance Monitoring System Using Facial

Recognition Context level 1

This figure shows the develop attendance system using facial recognition,

member’s needs registration or enrollment to the system. The worker register’s the

member’s data to the system. The data are saved in the database. It also shows how

the attendance process are done, the user can log in using their face as ID , the system

will authenticate it by matching the face in the database and if the entered face id

successfully match the system will mark the attendance and save it to the attendance

table.
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA

Figure 9: Data Flow Diagram of Attendance Monitoring System Using Facial

Recognition Context level 2

This figure shows the system are able to send notification through SMS

technology to the inactive members. The workers will able to determine inactive

member and are able to produce report. Sorting of member’s information are now

easy and convenient.

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
Haar Cascade Classifiers

A Haar Cascade is based on “Haar Wavelets” which Wikipedia defines as: A

sequence of rescaled “square-shaped” functions which together form a wavelet

family or basis. It is based on the Haar Wavelet technique to analyze pixels in the

image into squares by function. This uses machine learning techniques to get a high

degree of accuracy from what is called “training data”. This uses “integral image”

concepts to compute the “features” detected. Haar Cascades use the Adaboost learning

algorithm which selects a small number of important features from a large set to give

an efficient result of classifiers.

Haar Cascades use machine learning techniques in which a function is trained

from a lot of positive and negative images. This process in the algorithm is feature

extraction.

Figure10: Illustration of feature extraction Haar Cascade in facial detection

In feature extraction, the algorithm uses training data to best identify features that it

can consider a face.

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA

Figure11: Illustration of Brief feature extraction Haar Cascade in facial

detection

This is a brief illustration of Features Extraction and the difference between

Face Detection and Face Recognition. Face detection is about locating, while face

recognition is about identifying.

The researcher uses the detectMultiscalemodule from OpenCV. What this

does is create a rectangle with coordinates (x,y,w,h) around the face detected in the

image. This contains code parameters that are the most important to consider.

 ScaleFactor: The value indicates how much the image size is reduced at each

image scale. A lower value uses a smaller step for downscaling. This allows the

algorithm to detect the face. It has a value of x.y, where x and y are arbitrary

values you can set.

 minNeighbors: This parameter specifies how many “neighbors” each

candidate rectangle should have. A higher value results in less detections but it
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
detects higher quality in an image. You can use a value of X that specifies a

finite number.

 minSize: The minimum object size. By default it is (30,30). The smaller the

face in the image, it is best to adjust the minSize value lower. When a face is

detected, a green rectangle will be generated around the face. A viewer window

will also pop-up to show the results.[26]

Face Recognition: Understanding LBPH Algorithm

Local Binary Pattern (LBP) is a simple yet very efficient texture operator

which labels the pixels of an image by thresholding the neighborhood of each pixel

and considers the result as a binary number. It was first described in 1994 (LBP) and

has since been found to be a powerful feature for texture classification. It has further

been determined that when LBP is combined with histograms of oriented gradients

(HOG) descriptor, it improves the detection performance considerably on some

datasets. Using the LBP combined with histograms we can represent the face images

with a simple data vector.

Step-by-Step

Now that we know a little more about face recognition and the LBPH, let’s go further

and see the steps of the algorithm:

1. Parameters: the LBPH uses 4 parameters:

 Radius: the radius is used to build the circular local binary pattern and represents

the radius around the central pixel. It is usually set to 1.

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
 Neighbors: the number of sample points to build the circular local binary pattern.

Keep in mind: the more sample points you include, the higher the computational

cost. It is usually set to 8.

 Grid X: the number of cells in the horizontal direction. The more cells, the finer

the grid, the higher the dimensionality of the resulting feature vector. It is usually

set to 8.

 Grid Y: the number of cells in the vertical direction. The more cells, the finer the

grid, the higher the dimensionality of the resulting feature vector. It is usually set

to 8.

2. Training the Algorithm: First, we need to train the algorithm. To do so, we need to

use a dataset with the facial images of the people we want to recognize. We need to

also set an ID (it may be a number or the name of the person) for each image, so the

algorithm will use this information to recognize an input image and give you an output.

Images of the same person must have the same ID. With the training set already

constructed, let’s see the LBPH computational steps.

3. Applying the LBP operation: The first computational step of the LBPH is to create

an intermediate image that describes the original image in a better way, by highlighting

the facial characteristics. To do so, the algorithm uses a concept of a sliding window,

based on the parameters radius and neighbors.

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
The image below shows this procedure:

Figure12: Illustration of Applying the LBP operation

Based on the image above, let’s break it into several small steps so we can understand

it easily:

 Suppose we have a facial image in grayscale.

 We can get part of this image as a window of 3x3 pixels.

 It can also be represented as a 3x3 matrix containing the intensity of each pixel

(0~255).

 Then, we need to take the central value of the matrix to be used as the threshold.

 This value will be used to define the new values from the 8 neighbors.

 For each neighbor of the central value (threshold), we set a new binary value. We

set 1 for values equal or higher than the threshold and 0 for values lower than the

threshold.

 Now, the matrix will contain only binary values (ignoring the central value). We

need to concatenate each binary value from each position from the matrix line by
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
line into a new binary value (e.g. 10001101). Note: some authors use other

approaches to concatenate the binary values (e.g. clockwise direction), but the

final result will be the same.

 Then, we convert this binary value to a decimal value and set it to the central

value of the matrix, which is actually a pixel from the original image.

 At the end of this procedure (LBP procedure), we have a new image which

represents better the characteristics of the original image.

 Note: The LBP procedure was expanded to use a different number of radius and

neighbors, it is called Circular LBP.

Figure 13: Applying the Circular LBP operation:

It can be done by using bilinear interpolation. If some data point is between the

pixels, it uses the values from the 4 nearest pixels (2x2) to estimate the value of the

new data point.

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
4. Extracting the Histograms: Now, using the image generated in the last step, we

can use the Grid X and Grid Y parameters to divide the image into multiple grids, as

can be seen in the following image.

Figure 14: Extracting the Histograms

Based on the image above, we can extract the histogram of each region as follows:

 As we have an image in grayscale, each histogram (from each grid) will contain

only 256 positions (0~255) representing the occurrences of each pixel intensity.

 Then, we need to concatenate each histogram to create a new and bigger

histogram. Supposing we have 8x8 grids, we will have 8x8x256=16.384 positions

in the final histogram. The final histogram represents the characteristics of the

image original image.

The LBPH algorithm is pretty much it.

5. Performing the face recognition: In this step, the algorithm is already trained.

Each histogram created is used to represent each image from the training dataset. So,
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
given an input image, we perform the steps again for this new image and create a

histogram which represents the image.

 So to find the image that matches the input image we just need to compare two

histograms and return the image with the closest histogram.

 We can use various approaches to compare the histograms (calculate the distance

between two histograms), for example: euclidean distance, chi-square, absolute

value, etc. In this example, we can use the Euclidean distance (which is quite

known) based on the following formula:

Figure 15: Formula can use to calculate distance between two Histogram

 So the algorithm output is the ID from the image with the closest histogram. The

algorithm should also return the calculated distance, which can be used as a

‘confidence’ measurement. Note: don’t be fooled about the ‘confidence’ name, as

lower confidences are better because it means the distance between the two

histograms is closer.

 We can then use a threshold and the ‘confidence’ to automatically estimate if the

algorithm has correctly recognized the image. We can assume that the algorithm

has successfully recognized if the confidence is lower than the threshold

defined.[28
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
Design of Software, Systems, Product and/ or Processes

On the basis of the foregoing concepts, theories and findings of related

literature, studies and insights taken from them, a conceptual model was developed as

shown below.

Input Process Output

Knowledge Requirements
1. Database Planning – analyzing
the decision making
2. Python
and the requirements
3. Raspberry Pi need for the system. Development of
Design – designing the Attendance
4. JQuery
system physical and Monitoring System
5. Html logical to make it more with Facial
appropriate. Recognition using
6. Django framework
Raspberry pi3 for
Testing – Testing of
Hardware Requirements the system process by Ang Dating
trial and error method. DaanAlabang
7. Laptop
Chapter
8. Raspberry Pi3 Implementation –
implementation of the
9. Web cam Attendance Monitoring
system.
10. Sd Card

11. Connection Cables

Software Requirements
1. Linux OS

2. OpenCV libraries

3. SQLite3
Evaluation
4. Bootstrap

Figure 16: Conceptual Framework

The Conceptual Framework is composed of input, process and output. The

inputs for the proposed system states the necessary requirements for the system

development, software requirements and hardware requirements, the process shows

the stages that input will undergo.

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
System Architecture

Figure 17: System Architecture of the proposed Attendance Monitoring System

with Facial Recognition Using Raspberry Pi

The figure illustrates that the web camera will detect the user face Id and using

the Raspberry Pi it will compare the Face Id detected to the exiting face id stored in

database. When the Raspberry Pi locates the exact face id it will recognize the user.

The system will saved the date and time as attendance log of the user. The Admin will

be able to manage the system such as viewing of records and Attendance log, adding

/deleting user Accounts and generating reports.

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA

Figure 18: Block Diagram Outline of Proposed System

From the Figure 18 power supply is given to the raspberry pi which is the

heart of the proposed system. Pi camera is connected to the raspberry pi camera slot.

Camera captures the images of the students who are present in the class. Raspberry pi

takes those images as input images and compares the input images with the existing

image. This happens due to importing the open CV packages at the initial stage of the

development of the system. Admin tracks the attendance of the students periodically

or whenever required by the administration and finds the result. The result is

displayed on the monitor screen which is connected to the raspberry pi through the

Ethernet cable or HDMI to VGA converter.

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
DEVELOPMENT AND TESTING
Development Methodology
The researcher used Rapid Application Development method in developing

the system. Rapid Application Development is a software development methodology

that uses minimal planning in favor of rapid prototyping. Each phase of the

development is elaborated on this part of the study and discusses how the project was

conducted and developed.

Figure. 19 Rapid Application Development Prototyping

Phase 1: Requirement Planning

In this phase, the researchers gather information about the problem of the

organization. The proponents and the faculty discuss and agreed on the need of the

project, its scope, constraints and system requirement. Data were also collected

through online research in the internet for the proper content of the system. The

researcher also discussed the components on things that give solutions to the problem.

Phase 2: User Design

In this phase, the proponents design the system using Python. The target

user(s) is the Member’s of Ang Dating Daan Alabang Coordinating Center. The

developer design the System for the prefer target user(s) and make it user-friendly so
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
that won’t have hard time accessing it. However, the proponents are still working on

applying the design that the users want.

Phase 3: Construction

This phase focuses on the application and development of the system. The

developers construct the system based on python. Also in this phase the developers

also develop a prototype needed for the Attendance monitoring system with the use of

Raspberry pi 3 for facial recognition purposes.

Phase 4: Cut-over

In this phase, the system will tested for actual operation by users to

authenticate if the program and prototype meets the requirement of the users and to

validate as well if the programmer had satisfied the objective of the researcher. The

Attendance monitoring system with facial Recognition using Raspberry pi 3 will

introduce to the Ang Dating Daan Alabang chapter for testing and evaluation of the

performance of the developed system.

Testing Procedures

The testing procedure is needed by the proponents to properly address and

identify the possible errors and bugs that will appear on the system. Although, it did

not generally remove all the errors or bugs, but it at least helped the proponents

correct them and prevent them from reappearing in the future. The system features

were tested in a specified order to make sure that the functionality of the system was

meet and properly performs. The overall testing time is reduced in the RAD Prototype

model as the prototypes are independently tested during every iteration. However, the

data flow and the interfaces between all the components need to be thoroughly tested
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
with complete test coverage. Since most of the programming components have

already been tested, it reduces the risk of any major issues.

Table 1
Testing Procedures

Component/ Module Test Conducted

Face Detection module Test if single face is being detected well

Test if multiple faces are being detected
well
Database Module Test if detected faces are storing or not
Test if the data is storing into a file or
not
Face Recognition module Test if single face is recognizing or not.

Test if multiple faces are recognizing or

not.
Add User module Test if the system can add new user

Delete User Module Test if the system can delete existing

accounts

GUI Module Test if the GUI button functioning

Report Module Test if the system can export record

convertible into reports

Admin Module Test if admin can log in to the system.

The evaluation instrument was based on the characteristics and sub-

characteristics provided by ISO/IEC 25010:2011.

Respondents of the study were individual users of the system such as the 10

Information Technology (IT) Experts and 20 Actual Users. Purposive sampling is

used to select the number of respondents. Purposive sampling is a non-probability

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
sampling technique; it is a form of sampling in which the selection of the sample is

based on the judgment of the researchers as to which subjects.

The statistical used in the interpretation of data is weighted arithmetic mean as

shown in Table 2. The proponents used the Arithmetic mean to determine the average

responses of the Five option in each item, namely, 5(Strongly Agree), 4(Agree),

3(Undecided), 2(Disagree), 1(Strongly Disagree). The arithmetic means for each

software characteristics were computed. These computations were used to derive the

overall evaluation mean.

Table 2
Lickert Scale

Scale Range of Mean Value Interpretation

5 4.51 – 5.00 Strongly Agree

4 3.51 – 4.50 Agree

3 2.51 – 3.50 Undecided

2 1.51 – 2.50 Disagree

1 1.00 – 1.51 Strongly Disagree

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA

Description Of The Prototype

Figure 20.1 Isometric Diagram of the proposed prototype for the Attendance
Monitoring system
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA

Figure 20.2 Illustration Diagram of the proposed prototype for the Attendance
Monitoring system
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA

Figure 21 Schematic Diagram of the proposed prototype for the Attendance

Monitoring system

IMPLEMENTATION PLAN

The developed system ”Attendance Monitoring System with Facial

Recognition using Raspberry Pi” will be sent to Ang Dating Daan Alabang Chapter

right away after the revision to present it once more to the expected users. If the

organization wants to adopt the system, the researchers will hand over the system

together with its documentation. It will serve as a guide to the administration who will

be assigned to the system’s update and maintenance. There would be a letter of

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
agreement that the system will be handed over to the organization freely and the

researchers is no longer responsible for its update and maintenance. If the system will

be implemented, the researchers will conduct several strategies. Those strategies are

presented below.

Table 3
Implementation Plan of the Develop system

STRATERGY ACTIVITIES PERSONS DURATION

INVOLVED
Approval for Letter for the Dean Researchers, Dean 1 day
CITCS
System’s Creation Buying prototype Researchers 14 days
Spare parts,
Assembling
Prototype.

System’s Creating Researchers 30 days

Development Dashboard,
Training algorithm,
installing libraries
and software
needed, testing the
system, fixing bug
and enhancing
System’s features.
System’s Installation of the Researchers, MIS 5 hours
Installation system and staff, Administrator
required software
and hardware

Information Manual Admin 1 day

Distribution MIS staff,
Web Application Administrator
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
Training Hands on Training Admin, MIS staff 1–4
and Lecture Days

CHAPTER 4

RESULTS AND DISCUSSIONS

This chapter presents the project description, project structure project

capabilities and limitations and project evaluation of the study will be presented.

Project Description

The Attendance Monitoring System with Facial Recognition using Raspberry

Pi is developed to help the Ang Dating Daan Coordinating Center Alabang in

managing and handling their member’s information, monitor each of its status.

Record keeping and operations like reporting and monitoring members attendance

are the main focus of the system.

Figure 22 (The Attendance Monitoring System with Facial Recognition using

Raspberry Pi) Icon/Logo

Figure is designed icon/logo for the attendance monitoring system. It is simple

design that features the initials of the title itself to represent the main focus of the
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
system which is the facial recognition. The Designer use only minimal color pallet to

represent simplicity of the non-complex function of the system .

Figure 23 Home and Dashboard Page

Figure displays the home page and system’s dashboard. The homepage ia the

parent form of the dashboard. The home page contains the following buttons which

are the following:

1. Attendance

2. View members

3. Add members

4. Members Database.

The system’s dashboard displays member’s record statistics the number of

member per category. The Dashboard also displays the following:

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
1. Number of active members

2. Umbers of inactive members

3. Numbers of member per category such as groups of Adults and youth.

3. Formatted: Font: (Default) Times New Roman, 12 pt

Formatted: List Paragraph, Left, Space After: 0 pt, Outline
numbered + Level: 2 + Numbering Style: 1, 2, 3, … + Start
at: 1 + Alignment: Left + Aligned at: 0.5" + Tab after: 1" +
Project Structure Indent at: 1", Tab stops: Not at 1.9"

Figure 24 Login Form

Figure displays the login form of the system. The login form shows a simple white

design. The log in form is in small size and none-resizable.

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA

Figure 25 Database Record Page

Figure displays the record page. It contains the attendance detail of the members. This

feature can help the user search member’s record without refiguring the database.
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA

Figure 26 Add members

Figure a displays the member registry. It serves as their control panel of the database

and can do simple CRUD database operation. In addition to its feature is the print in

feature of the system where the user can choose when printing in any way the users

desire . .

Formatted: Tab stops: 1.64", Left + Not at 1.9"

PAMANTASAN NG LUNGSOD NG MUNTINLUPA
Formatted: Left

Figure 27 Actual Attendance Processing Formatted: Font: Not Italic

Formatted: Left

Formatted: Left
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
Figure 28 Attendance Feature

This Figure Show the attendance feature of the system. It has two option the Face Formatted: Left, Indent: First line: 0.3"

Recognition and Barcode Scanner. Although the Barcode System is still under

development.

Figure 29 Add User Feature Formatted: Font: Not Bold

Formatted: Font: Not Italic
Formatted: Centered
This figure shows that the system are able to add user that can access certain part of Formatted: Left

the system. Formatted: Font: Not Italic

Formatted: Centered

Formatted: Left
Formatted: Font: Not Bold, Italic

Formatted: Left
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
Figure 30 Authorization Access Control Formatted: Font: Not Italic

The system are able to grant authorization or access to the system. Formatted: Centered

Formatted: Font: Not Bold

Figure 31 Sample SMS Notification Receive By the Member Formatted: Centered

Formatted: Font: Not Italic

This figure shows the actual SMS message sent by the system to the inactive member. Formatted: Left
Formatted: Font: Not Bold

Project Capabilities and Limitation

The following are the capabilities and limitations of Development of an

Attendance Monitoring System with Facial Recognition using Raspberry Pi for Ang

Dating Daan Coordinating Center Alabang.

Capabilities

1. The system can perform basic CRUD database management functions. The

developers also provides an interactive user-interface.

2. The dashboard module is capable of acting as a data-analytics by presenting

real-time information in relation to member’s database records.

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
3. This system automate reports by displaying it on the dashboard real-time. In

addition the system also offers printing options for report documentation.

4. The Add new member’s database can be managed easily and updated real-

time.

5. The Member Records module provides a clear and less complex view of

member records with its sorting options.

6. The System can send notification through SMS notification to the inactive

members.

7. The system can perform Attendance through Facial recognition and barcode

scanning and manual encoding ID number as well.

Limitations

1. Development of an Attendance Monitoring System does not require internet

to function.

2. The system can only operate in windows and linux platforms with higher or

latest version.

3. Attendance Monitoring System is only limited to processing input data

records and storing data to the database.

4. Attendance Monitoring System dashboard can only display record’s data

and statistics.
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
5. The system process is only limited to attendance, view member, , add

member and member database.

To evaluate the project capabilities and limitations, the developed system

underwent actual testing and evaluation process with IT professionals and experts,

actual users and students as respondents.

Formatted: Space After: 8 pt

Project Evaluation

The developed system underwent actual testing and evaluation process. The

evaluation process was with the accordance of ISO/IEC 25010 2011. The evaluation

instrument provides a rating to scale the criteria for the prototype and software

materials, where five (5) is the highest and one (1) is the lowest. It suggests a software

metrics (Strongly Agree, Agree, Undecided, Disagree, Strongly Disagree). The

Testing results as shown in following tables were test conducted by forty seven (47)

evaluators, fifteen (15) actual users including the Workers and Church member. (25)

students with subjects related to software development and seven (7) IT experts in the

area of the System & IT professionals working in an information technology center

and management office. The system was also evaluated if it meets the project
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
objectives. The system's final prototype was evaluated by the evaluators hence some

changes and improvements are done with the final system output. The testing was

conducted in two cycles for each module during the system development. The testing

was done in two operating system, one in Linux and the other on Windows 10. The

system was subjected to 9 test cases to assess the functionality of each module. The

sample test cases with corresponding results for both cycles are presented in Table 4

and 5.

Table 7 shows the evaluation of the respondents of the study including users Formatted: Indent: First line: 0.5"

an users and five (3) students. The comments and suggestion provided and were noted

for recommendation purposes.

Formatted: Justified, Indent: First line: 0.5", Line spacing:

Double

Table 7
Summary of Evaluation Results by the Users

Indicators Mean Descriptive Meaning

Functional Suitability Agree

4.38

Performance Efficiency Agree

4.29

Usability Agree
4.45

Reliability Strongly Agree

4.68

Over All Mean 4.45 Agree

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
The summary of the overall mean score evaluation by the user as shown in

table 4 was 4.38 and rated as "Agree". The following area of evaluation were on

functional suitability which was scored 4.29 and was rated "Agree", another is on the

area of Performance Efficiency which was scored 4.45 and was rated "Agree", the

area of Usability was 4.68 and was rated " Strongly Agree" and the last area was the

Reliability that was scored 4.5 and was rated “Agree".

Table 8 shows the evaluation of the respondents of the study including ten

users in the same area of the system. The comments and suggestion provided by the

respondents were noted for recommendation purposes.

Formatted: Left

Formatted: Justified, Space Before: 12 pt, After: 10 pt, Line

spacing: Double

Formatted: Left
Table 8
Summary of Evaluation Results by the IT Expert

Indicators Mean Descriptive Meaning

Functional Suitability Strongly Agree

4.71

Performance Efficiency Strongly Agree

4.76

Usability Strongly Agree

4.64
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
Reliability Agree
4.36

Security Strongly Agree

4.74

Maintainability Strongly Agree

4.86

Portability Strongly Agree

4.67

Over All Mean 4.68 Strongly Agree

The summary of the overall mean score evaluation by the IT expert as shown

in table 6 was 4.68 and was rated " Strongly Agree". The following area of evaluation

were on Functional Suitability which was scored 4.71 and was rated " Strongly

Agree", on the area of Performance Efficiency which was scored 4.76 and was rated

"Strongly Agree", Usability is another area which was scored 4.64 and was rated

""Strongly Agree"", Reliability was also evaluated and gain a score of 4.36 and was

rated "Agree", another area is Security which scored 4.74 and was rated ""Strongly

Agree"", on the part of Maintainability it was scored by the valuator 4.86 and was

rated ""Strongly Agree"" and the last part was the portability which was scored 4.67

and was rated ""Strongly Agree".

Formatted: Space After: 10 pt

Table 9 illustrates the over-all mean both of actual users and IT Experts Formatted: Indent: First line: 0.5"

combined.

Table 9
Summary of Over-all Mean Evaluation Results

Indicators Mean Descriptive Meaning Formatted: Font: 11 pt

Formatted Table
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
Functional Suitability 4.54 Strongly Agree Formatted: Font: 11 pt

Performance Efficiency 4.52 Strongly Agree Formatted: Font: 11 pt

Usability 4.54 Strongly Agree Formatted: Font: 11 pt

Reliability 4.52 Strongly Agree Formatted: Font: 11 pt

Security 4.74 Strongly Agree Formatted: Font: 11 pt

Maintainability 4.86 Strongly Agree Formatted: Font: 11 pt

Portability 4.67 Strongly Agree Formatted: Font: 11 pt

Over All Mean 4.63 Strongly Agree Formatted: Font: 11 pt

Table 9 illustrates the over-all mean both of actual users and IT

Experts combined.

The summary of the overall mean score evaluation by the respondents as Formatted: Indent: First line: 0.5", Space Before: 12 pt

shown in tableb 6 was 4.63 and was rated "Strongly Agree". The following area of

evaluation were on Functional Suitability which was scored 4.52 and was rated

"Strongly Agree ", on the area of Performance Efficiency which was scored 4.52 and

was rated " Strongly Agree ". Usability is another area which was scored 4.54 and was

rated " Strongly Agree ", Reliability was also evaluated and pain a score of 4.52 and

was rated " Strongly Agree ", another area is Security which scored 4.74 and was

rated " Strongly Agree ", on the part of Me on the part of Maintainability it was

scored by the evaluator 4.86 and was rated " Strongly Agree " and the last part was

the portability which was scored 4.67 and was rated " Strongly Agree".
PAMANTASAN NG LUNGSOD NG MUNTINLUPA

Formatted: Left

Formatted: Centered
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
CHAPTER 5

SUMMARY OF FINDINGS, CONCLUSION AND RECOMMENDATION

This chapter presents the summary of findings in the developed system, test

and evaluation conducted, conclusions, as well as the recommendation based on the

result of the project evaluation, comments, and suggestions

Summary of Findings

An Attendance Monitoring System with Facial Recognition using Raspberry

Pi for Ang Dating Daan Coordinating Center Alabang is found out to be useful when

it comes to attendance automation aspects. Although the demographics of users find

the system more complex compared to using Microsoft excel, the system still got a

high rating value. The dashboard that displays the data statistics makes it more useful

and understandable to the actual users. In addition to it, they find the sorting options

more useful in retrieving data from the registry. The overall weighted average mean

of the developed system from IT Experts is 4.68 with a descriptive meaning of

“Strongly Agree”.

The proponents agreed that the system needs some improvement in its

features such as forms. The system controls should not be complex for users to use.

The experts also rated the developed system as easy to use based on its easy to

understand and user friendly graphic user interface. The small thought on the (UX)

user experience was also commended. Although its maintainability was not good

enough, the respondents expects that the proponent must improve its maintainability

when the development and implementation of the system is done. For actual users, the

developed system was rated 'Agree with the average weighted mean score of 4.45
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
rated as Strongly Agree. The proponent agreed that the developed system is a great

help for the beneficiary's needs and it also meets the project objectives and

requirements.

The overall weighted mean of the developed system is 4.63 and rated as "

Strongly Agree”, The proponents found out that the developed system is can be

described as a great step for their Church automation however, the users'

demographics who evaluated the system are ranging from 18-40 years old and they

lack of appropriate knowledge but has an interest in understanding or using the

system thoroughly. The problems were answered by the project through giving the

church a digital analysis of the data and information. The developed system acts and

perform as a data analytic.

With the data and information that the system can produced reports, and able

to notify inactive members through SMS notification integrated in the system as well

as sorting members information according to the user’s desire.

Conclusion

The developers used the input of users and IT Experts to broaden the

capability and quality of the developed system entitled “Development of an

Attendance Monitoring System with Facial Recognition using Raspberry Pi for Ang

Dating Daan Coordinating Center Alabang"

The following conclusions were derived based on the concerns stated in the

objectives of the study a of the study and results of the evaluation conducted
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
1. That “Development of an Attendance Monitoring System with Facial Recognition

using Raspberry Pi for Ang Dating Daan Coordinating Center Alabang " was design

with the following features:

a. That the system can create a database that contains attendance

information of the members.

b. That the automated system can create, modify, search and delete

member’s information.

c. That the system can capture live feed from camera to record

attendance times.

d. That automated system can link the information captured by the feed

to the database for accuracy results.

e. That the automated system can send notification thru SMS

notification.

f. That the automated system are able to produce reports for monitoring

g. That the system addressed all the beneficiary's concerns and complied

with the given project specifications during the planning period of the system

development

2. That the proponents design the system in compliance to the beneficiary’s requests

and specifications needed.

3. That the developed system has been successfully tested for its functional suitability,

performance efficiency, compatibility, usability, reliability maintainability and

portability by IT Experts and tested by the actual users on the area of functionality,

content, reliability and availability

 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
4. That the system answered the presented problems by making the analysis of all the

data can be used as a guide in decision making for the agency. The system can only

suggest possible alternative options incompletely addressing the problems

distinguished and determined by the system.

5. That the developed system were evaluated by the IT experts w valuated by the IT

experts with an overall mean score of 3.97. The developed system was rated "Agree"

and evaluated by the actual users with an overall mean score of 3.87 and was rated

"Agree from the evaluation prepared and adopted from ISO 25010:2011. 0.07 And

was rated "Agree" based

6. The developed system is ready for implementation upon the request agreement of

the proponents and the beneficiary.

Recommendation

After the evaluation and testing procedures done by IT experts and actual

users and based on the results of the study, some recommendations are cited as

follows:

1. That the development of the system should also aimed for the longevity of use of

the system and comply with the current and future situations of the beneficiary

2. That the developed system needs improvements in terms of interface complexity,

design preference of users and needs added information to pat the interest of future

users.
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
3. That the developed system should be easy to use by both current and future users to

maximize the longevity of the system.

4. That the developed system is can be subjected to changes and the future researcher

can insert additional functions and improvements to the actual developed system.

REFERENCES
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
[1]A Study of Various Face Detection Methods , Ms.Varsha Gupta1 , Mr. Dipesh
Sharma2,ijarccevol.3https://www.ijarcce.com/upload/2014/may/IJARCCE7G
%20%20a%20varsha%20A%20Study%20of%20Various%20Face.pdf
[2] Face Recognition Based on HOG and Fast PCA Algorithm Xiang-Yu Li(&) and
Zhen-Xian Lin
[3] Attendance System Using Face Recognition and Class Monitoring System,
ArunKatara1,Mr.Sudesh2,V.Kolhe3http://www.ijritcc.org/download/browse/V
olume_5_Issues/February_17_Volume_5_Issue_2/1489565866_15-
032017.pdf
[4] International Research Journal of Engineering and Technology (IRJET) e-ISSN:
2395-0056Volume: 05 Issue: 04 | Apr-2018 www.irjet.net p-ISSN: 2395-0072
[5] International Journal of Advanced Research in Computer and Communication
EngineeringVol. 4, Issue 2, February 20150
[6]https://www.google.com/url?sa=t&source=web&rct=j&url=https://www.theseus.fi/
bitstream/10024/114912/1/Minh%2BNguyen%2B-
%2Bthesis_final.pdf&ved=2ahUKEwiBzPPZjqfiAhWFdHAKHV7YD0IQFjA
BegQICRAF&usg=AOvVaw3pqnmAvkZ5hZ9A3T4mSM9L
[7] ISSN: 2350-0328International Journal of Advanced Research in Science,
Engineering and TechnologyVol. 4, Issue 5 , May 2017
[8] International Research Journal of Engineering and Technology (IRJET) e-ISSN:
2395-0056 Volume: 05 Issue: 03 | Mar-2018 www.irjet.net p-ISSN: 2395-
0072
[11] Twisha Patel and Bhumika Shah, “A Survey on Facial Feature Extraction
Techniquesfor Automatic Face Annotation”, IEEE International Conference
on Innovative Mechanisms for Industry Applications (ICIMIA 2017),
Bangalore, India.
[12] Jignesh J. Patoliya and Miral M. Desai, “Face Detection based ATM Security
System using Embedded Linux Platform”, IEEE 2017 2nd International
Conference for Convergence in Technology (I2CT),Mumbai, India.
[13] Mohamed Heshmat, Walaa M. Abd-Elhafiez, MohebGirgis and SehamElaw,
“Face Identification System in Video”, IEEE 2016 11th International
Conference onComputer Engineering & Systems (ICCES), Cairo, Egypt.
[14] Ardinintya Diva Setyadi, Tri Harsono and SigitWasista, “Human Character
Recognition Application Based on Facial Feature Using Face Detection”,
IEEE 2015 International Electronics Symposium (IES), Surabaya, Indonesia.
[15] ShubhamMathur, Balaji Subramanian, Sanyam Jain and KajalChoudhary,
“Human Detector and Counter Using Raspberry Pi Microcontroller”, IEEE
International Conference on Innovations in Power and Advanced Computing
Technologies i-PACT2017, Vellore, India.
 PAMANTASAN NG LUNGSOD NG MUNTINLUPA
[16] Li Cuimei, Qi Zhiliang, Jia Nan and Wu Jianhua, “Human face detection
algorithm via Haar cascade classifier combined with three additional
classifiers”, 2017 IEEE 13th International Conference on Electronic
Measurement & Instruments ICEMI’2017,Yangzhou, China.
[17] Hesham A. alabbasi and Floricamoldoveanu, “Human face detection from
images, based on skin color”, International Conference on System
Theory,Control and Computing, Sinaia, Romania,October 17-19, 2014.
[18]Jatin Sharma, ChandanChakraborty, Anbarasu M andShanmugasundaram M, “Iris
Movement Based Wheel Chair Control Using Raspberry Pi - A State of Art”,
International Conference on Innovations in Power and Advanced Computing
Technologies i-PACT2017, Vellore, India.
[19] International Conference on Science and Engineering for Sustainable
Development (ICSESD-2017) (www.jit.org.in)International Journal of
Advanced Engineering, Management and Science (IJAEMS) Special Issue-
1https://dx.doi.org/10.24001/icsesd2017.50 ISSN : 2454-
1311www.ijaems.com Page | 198
[20]https://www.stewright.me/2012/09/tutorial-install-phpmyadmin-on-your
raspberry-pi/
[21]
[22]
[23]
[24]
[25]
[26]
[27]
[28]
PAMANTASAN NG LUNGSOD NG MUNTINLUPA