Professional Documents
Culture Documents
Tribhuvan University Asian School of Management and Technology
Tribhuvan University Asian School of Management and Technology
Project Proposal
On
A Project Proposal for the Final Year Project submitted to the partial fulfillment of the
requirement for the degree of Bachelor of Science in Computer Science and Information
Technology awarded by Tribhuvan University.
Submitted by
Submitted to
Tribhuvan University
1. Introduction
In any educational administration, the student attendance record is one of the crucial issues
dealt with in any school, college, and university from time to time. Every organization has
its own method to do so, one of the approaches is taking attendance manually by calling
the roll number of students which is a tedious and time-consuming task. Therefore, many
institutes started deploying many other techniques for recording attendance like the use of
Radio Frequency Identification (RFID), iris recognition, fingerprint recognition, and so on.
In the RFID card system, each student is assigned a card with their corresponding identity
but there is a chance of card loss, or an unauthorized person may misuse the card for fake
attendance. While other biometrics systems such as fingerprint, iris, or voice recognition,
they all have their own flaws, and they are intrusive in nature [1].
On the other hand, the use of face recognition is one of the smart ways of marking
attendance. It can be easily acquirable and is non-intrusive. Face recognition involves two
steps, the first step involves the detection of faces, and the second step consists of the
identification of those detected face images with the existing database.
This proposed system can be applied to create attendance using Face recognition, which
involves the process of extracting key features from any facial image of a student captured
at the time he/she is entering the classroom. Upon its successful recognition, it proceeds to
mark that recognized student’s attendance automatically.
2. Problem Statement
Research shows that attendance is an important factor in student achievement. School
attendance is a powerful predictor of student outcomes. At the beginning and end of class,
it is usually checked by the teacher, but it may appear that a teacher may miss someone, or
some students answer multiple times pretending to be another student. Face recognition-
based attendance system is a problem of recognizing faces for taking attendance by using
face recognition technology based on information technology.
3. Objectives
The Attendance System using Face Recognition is designed to reduce the flaws present in
the traditional manual attendance system. Some major objectives of our proposed system
are:
a. To automate the daily attendance in schools/colleges.
b. To evaluate the attendance eligibility criteria of the student.
c. To reduce the chances of proxy attendance
4. Methodology
4.1. Requirement Identification
4.1.1. Study of Existing System / Literature Review
Various research has been done and various systems have been already implemented to
overcome the problem caused by the traditional way of marking attendance.
Authors in [2] proposed a model of an automated attendance system. The model focuses
on how face recognition incorporated with Radio Frequency Identification (RFID) detects
authorized students and counts them as they get in and get out of the classroom. The system
also keeps the data of every student registered for a particular course in the attendance log
and provides necessary information according to the need. The problem with this approach
is an unknown person can make use of a valid ID card and enter the university.
In [4], the authors proposed the implementation of face recognition using HOG and
machine learning. It will analyze the attendance of students using machine learning to ease
the daily routine of teachers and staff. The Histogram of Oriented Gradients (HOG) is used
to extract the features from the face using the dataset to classify the students. However, 100
% accuracy of this setup is not guaranteed as it might result in failure sometimes due to
environmental, noise, internet, and live web camera issues.
In [5], face recognition is used for marking the attendance of the student. Authors have
used Haar Cascade for face detection and the LBPH algorithm for face recognition with
maximum accuracy of almost 80% for face recognition.
The authors in [7] have proposed an attendance system that marks the attendance of the
system using fingerprint. However, there are some limitations of fingerprint technology
like the inability to identify some students for poor fingerprints.
Source: https://www.amplifyre.com/articles/agile-methodology-for-software-
development
To develop the proposed system, timely delivery and quick adaption to requirement
changes are the major concerns. So agile method is the suitable method for the proposed
system.
4.3.2. Block Diagram
The block diagram of the proposed system is given below:
4.3.3. Algorithm
CNN:
A convolutional neural network is a feed-forward neural network that is generally used to
analyze visual images by processing data with a grid-like topology [8]. It’s also known as
ConvNet. In CNN, every image is represented in the form of an array of pixel values.
A convolution neural network has multiple hidden layers that help in extracting information
from an image. The steps involved to recognize an image using CNN are:
a. The pixels from the image are fed to the convolutional layer that performs the
convolution operation.
b. It results in a convolved map.
c. The convolved map is applied to a ReLU function to generate a rectified feature map.
d. The image is processed with multiple convolutions and ReLU layers for locating the
features.
e. Different pooling layers with various filters are used to identify specific parts of the
image.
f. The pooled feature map is flattened and fed to a fully connected layer to get the final
output.
5. Expected Outcome
The proposed system aims to build an attendance system using face recognition techniques.
The proposed system will be able to mark attendance via face Id. It will detect faces via
webcam and then recognize the faces. After recognition, it will mark the attendance of the
recognized student and update the attendance record.
6. References