JOURNAL OF CRITICAL REVIEWS

ISSN- 2394-5125 VOL 7, ISSUE 12, 2020

FACE RECOGNITION BASED ATTENDANCE

SYSTEM USING DEEP LEARNING TECHNIQUES
T. PRANEETH1, K. RAJESH2, U. NAGA RAJU3, DR. SUNEETHA MANNE4
1.2.3
Student, Department of Information Technology, VR Siddhartha Engineering College, Andhra Pradesh, India
4
Professor,Department of Information Technology, V R Siddhartha Engineering College, Andhra Pradesh, India

ABSTRACT:The most tiring task in any organization is attendance marking. In this we want to propose an
automated attendance management system which tackles the predicament of recognition of faces in biometric
systems subject to different real time scenarios such as illumination, rotation and scaling. This model incorporates
a camera that captures input image, an algorithm to detect a face from the input image, encode it and recognize the
face and mark the attendance in an Excel-sheet. Initially the system camera captures the image and store that image
in a database after storing training process takes place based upon the image from which the faces are recognized
from the database and attendance is calculated on basis of several Deep Learning algorithms like Local Binary
Pattern Histogram algorithm, Convolutional Neural networks.
KEYWORDS:Haar Cascade, Face Recognition, Face Detection, Deep Learning, Python

I. INTRODUCTION
Attendance is an important part of daily classroom evaluation. At the beginning and ending 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.
So, for this every organization has adopted its own method for AMS. Some continue with the traditional method
for taking attendance manually while some have adopted the biometric techniques. The traditional method makes
it difficult to verify students one-by-one in a large classroom environment. Moreover, the manual labor involved in
computing the attendance percentage becomes a major task. The Radio Frequency Identification (RFID) helps to
identify a large number of crowds using radio waves [1]. Face recognition-based attendance system is a problem of
recognizing face for taking attendance by using face recognition technology based on high definition monitor
video and other information technology.
The face recognition is an integral part of biometrics. In biometrics, basic traits of human are matched to the
existing data. Facial features are extracted and implemented through algorithms, which are efficient and some
modifications are done to improve the existing algorithm models. Computers that detect and recognize faces could
be applied to a wide variety of practical applications including criminal identification, security systems, identity
verification etc. like Real-time face verification system on a cell-phone using advanced correlation filters [2].
The face recognition system generally involves two stages:
Face Detection: where the input image is searched to find any face, then image processing cleans up the facial
image for easier recognition.
Face Recognition: where the detected and processed face is compared to the database of known faces to decide
who that person is.
II. LITERATURE SURVEY
Fingerprint reading systems have high installation costs. Furthermore, only one student at a time can use a portable
finger recognition device, which makes it a time-consuming process. In the case of a fixed finger recognition
device at the entrance of the classroom, attendance-taking should be done under the teacher's supervision so that
students do not leave after the finger recognition, which makes the process time-consuming for both the teacher
and the students by using these .a lot of time can be saved by the lecturers with automated Attendance Management
System (AMS), where the attendance can be updated by capturing the images of the students by a high definition
camera without the human intervention
The various methods used for face recognition based attendance system using various algorithms are shown by
several authors at which the each other describes the several features of their proposed systems like FaceTime–
Deep Learning Based Face Recognition Attendance System [3]. Here in this the author mainly discuss about the
entire process of developing a Face Recognition component for detecting the faces through the advances in Deep

2516
 JOURNAL OF CRITICAL REVIEWS

ISSN- 2394-5125 VOL 7, ISSUE 12, 2020

Learning techniques. Attendance Management System Using Hybrid Face Recognition Techniques [4]. These
authors mainly describes about an Automated Attendance Management System at which the detection and
recognition of faces mainly done through Viola-Jones Algorithm. Face Recognition-Based Mobile Automatic
Classroom Attendance Management System [5]. These authors mainly describes about a flexible real time face
recognition based attendance system at which the recognition process is done by a filtering system based upon the
Euclidean distances that are obtained by Local Binary Patterns are developed. A Smart School by Using an
Embedded Deep Learning Approach for Preventing Fake Attendance [6]. These authors mainly describes about an
embedded smart school system at which the faces are recognized through by using IOT technologies.
The proposed systems mainly deals with improving the performance of existing attendance management systems
in the following ways:
 Automatic tracking of the records of the students
 Minimizing the manual labour and pressure on the lecturers for accurate marking of the attendance
 Minimizing the time required for marking attendance and maximizing the time required for actual
teaching process.
 Increase the efficiency of the overall system improving the security.
III. PROBLEM STATEMENT
The concept of face recognition is to give a computer system the ability of finding and recognizing human faces
fast and precisely in images or videos. Numerous algorithms and techniques have been developed for improving
the performance of face recognition. Recently Deep learning has been highly explored for computer vision
applications. Human brain can automatically and instantly detect and recognize multiple faces. But when it comes
to computer, it is very difficult to do all the challenging tasks on the level of human brain. The face recognition is
an integral part of biometrics. In biometrics, basic traits of human are matched to the existing data. Facial features
are extracted and implemented through algorithms, which are efficient and some modifications are done to
improve the existing algorithm models. Computers that detect and recognize faces could be applied to a wide
variety of practical applications including criminal identification, security systems, and identity verification like
Real-time face verification system on a cell-phone using advanced correlation filters.
IV. METHODOLOGY
4.1 Proposed System:
The method proposed in this paper is marking attendance using face recognition technique. As shown in Fig - 1,
the attendance is recorded by using a camera that will stream video of students, detect the faces in the image and
compare the detected faces with the student database and mark the attendance. The proposed system architecture is
shown in Fig 1.

Fig 1: Proposed System Architecture Diagram

The proposed system face recognition-based attendance system can be divided into five main modules. The
modules and their functions are defined as follows.
 Image Capture.

2517
 JOURNAL OF CRITICAL REVIEWS

ISSN- 2394-5125 VOL 7, ISSUE 12, 2020

 Face Detection.
 Understanding Haar Cascades.
 Database Development
 Post Processing.
A. Image Capture:
The camera is fixed at a distance from the entrance to capture the frontal image of the students. And remaining
process goes for face detection.
B. Face Detection:
Detecting facial landmarks is a subset of the shape prediction problem. Facial landmarks such as eyes, eyebrows,
nose, mouth, jaw line were used to localize and represent salient regions of the face. Given an input image, a shape
predictor attempts to localize key points of interest along the shape. In the context of facial landmarks, our goal
was to detect important facial structures on the face using shape prediction methods. Detecting facial landmarks is
therefore involves localizing the face in the image and detecting the key facial structures on the face ROI. Dlib and
OpenCV were used to detect facial landmarks in an image.
Open CV uses two types of classifiers, LBP (Local Binary Pattern) and Haar Cascades.
C. Face detection using OpenCV’sHaar Cascades:
Using the Haar feature-based cascade classifiers is an effective object detection method proposed by Paul Viola
and Michael Jones in their paper, "Rapid Object Detection using a Boosted Cascade of Simple Features" in
2001[7]. It is a machine learning based approach where a cascade function is trained from a lot of positive and
negative images. It is then used to detect objects in other images. Here the types of Haar Features and Haar features
applied on an image is shown below in Fig 2 and Fig 3.

Fig 2: Types of Haar Features

Fig 3: Haar features applied on an image

D. Face Detection using a model for predicting facial landmarks
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.
The algorithm used to detect the face in the image matter less, instead what matters is given the face region where
we can apply facial landmark detector. The Face Landmark Estimation for an image is shown below in Fig 4.

2518
 JOURNAL OF CRITICAL REVIEWS

ISSN- 2394-5125 VOL 7, ISSUE 12, 2020

Fig 4: Face Landmark Estimation.

Regardless of which dataset is used, the same dlib framework can be leveraged to train a shape predictor on the
input training data which can be useful if one likes to train facial landmark detectors or custom shape predictors.
The Landmarks that are detected on an Face image is shown below in Fig 5.

Fig 5: Face Landmarks Detected.

E. Database Development
In this system collection of every individual is required. This database development phase consists of image
capture of every individual student and our proposed system it is face, and after it is enhanced using pre-processing
techniques and to be stored in the database.
F. Post Processing
In the proposed system, after recognizing the all faces of the students and names of individuals are updated into an
excel sheet is created by exporting mechanism present in the database.
In this dataset initially images of different persons in different directions are taken and are stored in the database
based on the images taken and after storing the image in the database face recognition process will takes place here
in the recognition process it usually checks the new image and compares with the old images that are stored in the
database. If the image of the person is found in the database then attendance will be assigned to the particular

2519
 JOURNAL OF CRITICAL REVIEWS

ISSN- 2394-5125 VOL 7, ISSUE 12, 2020

person based upon his id and name i.e., initially provided by the person and the attendance will be provided to the
person in the form of Excel sheet.
4.2 Proposed Algorithm:
1. Capture the student’s image through camera.
2. Detect each and every individual face by apply face detection algorithm.
3. Extract the ROI (Region of Interest) in rectangular bounding box.
4. Converting to gray scale, apply histogram equalization.
5. If image captured then Store in database. Else Apply LBPH (for feature extraction) Apply SVM (for
classification) End if.
6. Post-processing.
Flow Chart:
Here the complete process of the proposed system is shown below in the form of a Flow chart in Fig 6

Fig 6: Flow chart of Proposed System

V. SOFTWARE DESCRIPTION
The Software technologies are used for the project has been mentioned below:
5.1 PYTHON
Python is an easy to learn, powerful programming language. It has efficient high-level data structures and a simple
but effective approach to object-oriented programming. Python’s elegant syntax and dynamic typing, together
with its interpreted nature, make it an ideal language for scripting and rapid application development in many areas
on most platforms.
The Python interpreter is easily extended with new functions and data types implemented in C or C++ (or other
languages callable from C). Python is also suitable as an extension language for customizable applications.
5.2 OPEN CV
Open CV (Open Source Computer Vision Library) is an open source computer vision and machine learning
software library. Open CV was built to provide a common infrastructure for computer vision applications and to

2520
 JOURNAL OF CRITICAL REVIEWS

ISSN- 2394-5125 VOL 7, ISSUE 12, 2020

accelerate the use of machine perception in the commercial products. Being a BSD-licensed product, Open CV
makes it easy for businesses to utilize and modify the code. It is free for both commercial and non-commercial use.
The software tools are used for the project has been mentioned below:
 Microsoft Excel
 PyCharm Libraries
 Pandas
 Numpy
 Scipy
 Matplotlib
 Tensorflow
 Keras
 Tkinter
VI. EXPERIMENTATION AND RESULT ANALYSIS
The results that are obtained for the proposed system by various alternatives like by using Live Camera is shown in
Fig 7, by taking input as an image for the recognition process is shown in Fig 8 and the resultant output which is
generated based upon the faces detected is shown in the form of Ex-Celsheet in below Fig 9.

Fig 7: Face Recognition for Live Camera

Fig 8: Face Recognition for an input image

2521
 JOURNAL OF CRITICAL REVIEWS

ISSN- 2394-5125 VOL 7, ISSUE 12, 2020

Fig 9: Generation of report in an excel sheet.

VII. CONCLUSION
Nowadays, various attendance and monitoring tools are used in practice in industry regardless fact that these
solutions are mostly automatic, they are still prone to errors.
In this Face Recognition based attendance system, a new deep learning based face recognition attendance system is
proposed. The entire procedure of developing a face recognition component by combining state of-the-art methods
and advances in deep learning is described. It is determined that with the smaller number of face images along with
the proposed method of augmentation high accuracy can be achieved.
These results are enabling further research for the purpose of obtaining even higher accuracy on smaller datasets,
which is crucial for making this solution production-ready. The future work could involve exploring new
augmentation processes and exploiting newly gathered images in runtime for automatic retraining of the embedded
data. Developing a specialized classifying solution for this task could potentially lead to achieving higher accuracy
on a smaller dataset. This deep learning based solution does not depend on GPU in runtime. Thus, it could be
applicable in many other systems as a main or a side component that could run on a cheaper and low-capacity
hardware, even as a general-purpose Internet of things (IoT) device.
VIII. FUTURE STUDY
In this project, it is observed that only faces are detected only when the person face is clearly visible and when the
face of a person cannot be detected when the person is standing in any other direction so for this further study is
required for detecting the faces of the person clearly in all directions by using further deep learning algorithms.
REFERENCES
1. T.S.Lim, ―RFID based Attendance System‖, IEEE Symposium on Industrial Electronics and
Applications, Oct 2009, vol 2, pp. 778-782.
2. C.K. Ng, M.Savvides ―Real-time face verification system on a cell-phone using advanced correlation
filters‖, IEEE Workshop on Automatic Identification Advanced Techniques .
3. Marko Arsenovic ; SrdjanSladojevic ; AndrasAnderla ; DarkoStefanovic ―FaceTime — Deep learning
based face recognition attendance system‖ 2017 IEEE 15th International Symposium on Intelligent
Systems and Informatics (SISY) .
4. Nazare, KanchanJayant ―Attendance Management System Using Hybrid Face Recognition Techniques‖
2016 IEEE International Conference on Computational Intelligence and Computing Research .
5. RefikSamet ;MuhammedTanriverdi ―Face Recognition-Based Mobile Automatic Classroom Attendance
Management System‖ 2017 International Conference on Cyberworlds (CW) .

2522
 JOURNAL OF CRITICAL REVIEWS

ISSN- 2394-5125 VOL 7, ISSUE 12, 2020

6. Nashwan Adnan Othman ―A Smart School by Using an Embedded Deep Learning Approach for
Preventing Fake Attendance‖ 2019.
7. Paul Viola and Michael Jones in their paper "Rapid Object Detection using a Boosted Cascade of Simple
Features" in 2001.
E. Rekha ; P. Ramaprasad ―An efficient automated attendance management system based on Eigen Face
recognition ― 2017 7th International Conference on Cloud Computing, Data Science & Engineering –
Confluence .
8. ShubhobrataBhattacharya ;GowthamSandeepNainala ; Prosenjit Das ; AurobindaRoutray ―Smart
Attendance Monitoring System (SAMS): A Face Recognition Based Attendance System for Classroom
Environment‖ 2018 IEEE 18th International Conference on Advanced Learning Technologies (ICALT) .
9. Omar Abdul RhmanSalim ;RashidahFunkeOlanrewaju ; Wasiu Adebayo Balogun ―Class Attendance
Management System Using Face Recognition ― 2018 7th International Conference on Computer and
Communication Engineering (ICCCE).

2523