Chapter 1

Introduction

1.1 Overview

The automated attendance android application is aimed at providing a new, quick and
easy way of registering attendance. It tries to reduce the nuances of the traditional or
manual process of marking attendance in which the teacher has to call out the roll number
of every student in the class and mark his/her attendance after he/she has acknowledged
or responded to it. An online system has been developed which aims to reduce the
duration of the entire attendance taking process and reduce proxies entirely. Student
participation is recorded by utilizing the camera connected to the phone, detect the faces
in image and contrast the distinguished appearances and the database and mark the
attendance.

1.2 Issues Involved

The problem in existing attendance system is that it is tedious and a long process. Manual
process of marking attendance in which the teacher has to call out the roll number of
every student in the class and mark his/her attendance after he/she has acknowledged or
responded to it. This process may result in proxy attendance. So to avoid this situation
face recognition attendance system can come in handy. The main objectives of this
project are
1. Marking of daily students’ attendance.
2. Daily provision to check in personal attendance by employee of the college.
3. To produce the attendance statistics which can be viewed by HOD, directors and
staff on daily, monthly and yearly basis.

1.3 Proposed solution

The offline attendance system using an android device is a very effective tool which can
be used to a great extent. The system is portable and can be easily installed and used on
any mobile phone running Android OS. Also, it will eliminate the tedious work of the

1
teachers of maintaining different attendance sheet for different classes and different
subjects. The system will also avoid number of proxies in a class as the teacher will have
constant eye contact with the class.
This project can be used in hostel and other areas also where attendance is important. It
can be used for elimination false attendance.

2
 Chapter 2
Literature Survey

2.1 Modules
The aim of this project is to contribute to the solution of the problem of incorrect
attendance.
The proposed modules for this project are as follows:

A. Student Management: This constitutes the first phase of our project module. This
section consists following parameters:
1. Student Registration Form: The student appears as a new candidate for
registration. Registration consists of adding each candidate’s personal details.
2. Student Face detection: The newly registered candidate’s face gets detected for
the very first time and stored in the database.
B. Attendance System: This constitutes the second phase of our project module. The
recognition of each individual student takes place by extracting the common features of
each individual by using image integral method. Then the face image is matched with the
image stored in the database (MS SQL) and the attendance is marked for the candidate
only if the facial feature of the newly captured image matches with the already stored
image.
C. Exit: It takes the control out of the module.
The design and development of the system will follow the waterfall model as described in
figure 2.1.1 which is linear sequential design of steps followed.

3
 Figure 2.1.1 waterfall model
2.2 Existing Application
Countless systems have been developed in schools and industries to keep a track of the
attendance. These systems are good but they are plagued with performance and
scalability problems. The following systems are implemented in chronological order.
Biometric System

These systems usually take a unique element of the anatomy and use it for good
effect for example iris, palm, fingerprints etc. These systems are perfect for high
profile security agencies and are the need of the hour but these systems cannot be
used in educational institutions and factories. The data keeps scaling up and the
system needs to be maintained and refreshed for further use. The attendance
system using android devices provides a cheaper solution compared to the
biometric systems. The iris recognition system is another useful system and isn’t
susceptible to proxies but the main drawback being injuries to the eye. A
contingency plan could include storing data about both the eyes which would
increase the amount of storage resources required in an organization.
Bluetooth System

The system is the closest representation to the proposed system. The technology
makes use of electronic tags to facilitate automatic wireless identification, with a

4
 Bluetooth Smart enabled device. This system has high usability and proxy
removal techniques can be included to make the system perfect. However the
system is not scalable. This redundancy makes it a viable resource for a limited
population.
RFID System

The RFID systems are more popular. Students are given RFID cards along with
their Identity cards. These cards need to put in the RFID reader before the student
enters the classroom. Systems like these require permanent supervision because
students can sense two cards leading to a proxy and also improper usage can harm
the RFID reader. It also requires maintenance.

2.3 Problem with current scenario

 Traditionally attendance is tedious and a long process.

 Manual process of marking attendance in which the teacher has to call out the roll
number of every student in the class and mark his/her attendance after he/she has
acknowledged or responded to it.
 This process consumes a lot of time and may result in proxy attendance.

2.4 System Architecture

The architecture used in our project is the three tier architecture.

Figure 2.4.1 client server architechure

5
The advantage of using this type of model which is represented in figure 2.4.1 is that the
functionality is distributed across three independent systems and also that any of the tier
can be replaced or upgraded independently if the requirements or the technology changes.
The working of the system is depicted as follows:

A. Image Acquisition: The system consists of a camera that captures the images
of the students and sends it to the image pre-processing. Then that image is
sends for face detection.

B. Face Detection: This process separates the facial area from the rest of the
background image. The faces which are stored in the database.

C. Face Recognition: The face image is then compared with the stored image. If
the face image is matched with the stored image then the face is recognized.

D. Marking Attendance: For the student with recognized face the attendance will
be marked for the day.

6
 Chapter 3
Analysis Requirements

3.1 Software Requirements

Simple User Interface Attendance system generally have very simple interfaces, showing
only what is necessary to continue the marking of attendance. With this is mind we will
use very simple screen interface that will display the previous attendance in tabular form.
Timely Response the system should mark the attendance in a few seconds, rather than

minutes.

3.2 Hardware Requirements

 200 MHz processor

 32 MB of RAM
 32 MB of storage
 Front Camera

3.3 Use Case Model and Data Flow Model

Figure 3.3.1 Use Case Diagram

7
 Figure 3.3.2Data Flow Diagram

3.4 Use Case Description

A use case diagram in the unified modeling language (UML) is a type of behavioral
diagram defined by and created from a use case analysis. Its purpose is to present a
graphical overview of the functionality provided by the system in terms of actors, their
goals (represented as use case), and any dependencies between those use cases. The main
purpose of a use case diagram is to what system functions are performed for which actor.
Roles of the actor in the system can be depicted. Interactions among the actors are not
shown in the diagram.
The proposed System represented by the above use case diagram will have following

module:

8
Admin module
 The attendance will be marked on the basis of the face recognition automatically.
 Hence no need to have a person to mark the attendance and ease for the students.
Users
 There will be two types of users student and teacher.
 The teacher will be able to see the attendance of the complete class.
 Student will be able to his/her overall attendance.

Actor Description

User Someone who uses the system to

engage in the process.

Administrator Allowed to carry out the administrative

tasks.

Table 3.4 Use Case Description

9
 METHODOLOGY

New user registration-

Information like First Name, Last Name, Contact Number, Address, ID

Number along with an image shall be stored in database.

SQLite is a opensource SQL database that stores data to a text file on a

device. Android comes in with built in SQLite
database implementation. SQLitesupports all the
relational database features.

User interface-

We propose an easy to use application.

New User Registration

Camera Interface

Why ,when and how?

Detect face and capture image

Match image with images in database

If match found :

mark attendance

Else

exit/re-capture

Capture-

The Camera Interface will capture an image in BitMap format

10
Detection-

Find faces and landmarks such as eyes, nose and mouth in photos.

Using FaceDetector Feature Android

java.lang.Object

↳ android.media.FaceDetector

Identifies the faces of people in a Bitmap graphic object.

Recognition using eigen faces-

Search for one-to-many matches. Answers: “Who is this person?” Cross

check from database. This will be implemented using OpenCV SDK. It’s an
SDK for image manipulation, color detection and face detection.

Eigen Face Method:

We make use of a mathematical tool called principal component

analysis(PCA). PCA is used to remove information not useful and thus
reduces dimension of data and accurately decompose the face structure into
orthogonal principal components known as eigen faces.

Each eigen face represents only certain features of face which may or may
not be present in original image. It can recognize presence of small onjects
in any face as well as relative distance between these objects and these
features are known as eigen faces. Thus similar face possess similar features
to similar degrees.

11
 Chapter 4
Design

System design is the process of defining the architecture , components, modules,

interfaces and data for a system to satisfy specified requirements. We have tried to
explain system design of our attendance system using sequence diagram and entity
relationship diagram.

4.1 Sequence Diagram

Fig4.1.1Sequence Diagram for New User

12
Fig 4.1.2 Sequence Diagram for Marking Attendance

13
 Chapter 5
Conclusion

The main objective of the project is to develop a system that will be used to identify the
faces of the student and mark their attendance automatically. The need is to develop a
database where all information will be stored and to develop a android interface.
Developed interface will have two interfaces one for user and one for administrator. The
logs that the system keeps is an important aspect of the system which will help the
administrator to find user attendance and class as it exists in the database. It is therefore
important to maintain a database updated continuously that aims to cover student’s
attendance. Currently teachers rely on manual process of role call . It is time consuming
and monotonous to make the complete attendance process.This is where our system
comes to the aid. It is designed to meticulously help teachers take attendance without
manual interference.The system works on the real time data provided by the institutes
itself to increase reliability and increasing transparency for students. The learning made
in the process was the fact that possibility of not retrieving the correct answer exists. A
usable system will be designed, developed and deployed to webserver is however an
achieve.

14