Published by : International Journal of Engineering Research & Technology (IJERT)

http://www.ijert.org ISSN: 2278-0181

Vol. 9 Issue 05, May-2020

Face Recognition based Attendance Management

System
Smitha, Pavithra S Hegde, Afshin
Dept. of Computer Science and Engineering
Yenepoya Institute of Technology
Moodbidri, India

Abstract— In this digital era, face recognition system plays a face is found in the database. This new system will consume
vital role in almost every sector. Face recognition is one of the less time than compared to traditional methods.
mostly used biometrics. It can used for security, authentication,
identification, and has got many more advantages. Despite of II. LITERATURE SURVEY
having low accuracy when compared to iris recognition and Authors in [3] proposed a model of an automated
fingerprint recognition, it is being widely used due to its attendance system. The model focuses on how face
contactless and non-invasive process. Furthermore, face recognition incorporated with Radio Frequency Identification
recognition system can also be used for attendance marking in (RFID) detect the authorized students and counts as they get
schools, colleges, offices, etc. This system aims to build a class
attendance system which uses the concept of face recognition as
in and get out form the classroom. The system keeps the
existing manual attendance system is time consuming and authentic record of every registered student. The system also
cumbersome to maintain. And there may be chances of proxy keeps the data of every student registered for a particular
attendance. Thus, the need for this system increases. This system course in the attendance log and provides necessary
consists of four phases- database creation, face detection, face information according to the need.
recognition, attendance updation. Database is created by the In this paper [4], authors have designed and implemented
images of the students in class. Face detection and recognition is an attendance system which uses iris biometrics. Initially, the
performed using Haar-Cascade classifier and Local Binary attendees were asked to register their details along with their
Pattern Histogram algorithm respectively. Faces are detected unique iris template. At the time of attendance, the system
and recognized from live streaming video of the classroom.
Attendance will be mailed to the respective faculty at the end of
automatically took class attendance by capturing the eye
the session. image of each attendee, recognizing their iris, and searching
for a match in the created database. The prototype was web
Keywords—Face Recognition; Face Detection; Haar-Cascade based.
classifier; Local Binary Pattern Histogram; attendance system; In [5], authors proposed an attendance system based on
facial recognition. The algorithms like Viola-Jones and
I. INTRODUCTION Histogram of Oriented Gradients (HOG) features along with
Traditional method of attendance marking is a tedious task Support Vector Machine (SVM) classifier were used to
in many schools and colleges. It is also an extra burden to the implement the system. Various real time scenarios such as
faculties who should mark attendance by manually calling the scaling, illumination, occlusions and pose was considered by
names of students which might take about 5 minutes of entire the authors. Quantitative analysis was done on the basis of
session. This is time consuming. There are some chances of Peak Signal to Noise Ratio (PSNR) values and was
proxy attendance. Therefore, many institutes started implemented in MATLAB GUI.
deploying many other techniques for recording attendance Authors in [6] researches to get best facial recognition
like use of Radio Frequency Identification (RFID) [3], iris algorithm (Eigenface and Fisherface) provided by the Open
recognition [4], fingerprint recognition, and so on. However, CV 2.4.8 by comparing the Receiver Operating
these systems are queue based which might consume more Characteristics (ROC) curve and then implemented it in the
time and are intrusive in nature. attendance system. Based on the experiments carried out in
Face recognition has set an important biometric feature, this paper, the ROC curve proved that, Eigenface achieves
which can be easily acquirable and is non-intrusive. Face better result than Fisherface. System implemented using
recognition based systems are relatively oblivious to various Eigenface algorithm achieved an accuracy rate of 70% to
facial expression. Face recognition system consists of two 90%.
categories: verification and face identification. Face In [7], authors proposed a method for student attendance
verification is an 1:1 matching process, it compares face system in classroom using face recognition technique by
image against the template face images and whereas is an 1:N combining Discrete Wavelet Transforms (DWT) and Discrete
problems that compares a query face images [1]. Cosine Transform (DCT). These algorithms were used to
The purpose of this system is to build a attendance system extract the features of student’s face followed by applying
which is based on face recognition techniques. Here face of Radial Basis Function (RBF) for classifying the facial
an individual will be considered for marking attendance. objects. This system achieved an accuracy rate of 82%.
Nowadays, face recognition is gaining more popularity and
has been widely used. In this paper, we proposed a system III. PROPOSED SYSTEM
which detects the faces of students from live streaming video All the students of the class must register themselves by
of classroom and attendance will be marked if the detected entering the required details and then their images will be

IJERTV9IS050861 www.ijert.org 1190

(This work is licensed under a Creative Commons Attribution 4.0 International License.)
Published by : International Journal of Engineering Research & Technology (IJERT)
http://www.ijert.org ISSN: 2278-0181
Vol. 9 Issue 05, May-2020

captured and stored in the dataset. During each session, faces Here we are using detectMultiScale module from OpenCV.
will be detected from live streaming video of classroom. The This is required to create a rectangle around the faces in an
faces detected will be compared with images present in the image. It has got three parameters to consider- scaleFactor,
dataset. If match found, attendance will be marked for the minNeighbors, minSize. scaleFactor is used to indicate how
respective student. At the end of each session, list of much an image must be reduced in each image scale.
absentees will be mailed to the respective faculty handling minNeighbors specifies how many neighbors each candidate
the session. rectangle must have. Higher values usually detects less faces
The system architecture of the proposed system is given but detects high quality in image. minSize specifies the
below, minimum object size. By default it is (30,30) [8]. The
parameters used in this system is scaleFactor and
minNeighbors with the values 1.3 and 5 respectively.
3. Face Recognition
Face recognition process can be divided into three steps-
prepare training data, train face recognizer, prediction. Here
training data will be the images present in the dataset. They
will be assigned with a integer label of the student it belongs
to. These images are then used for face recognition. Face
recognizer used in this system is Local Binary Pattern
Histogram. Initially, the list of local binary patterns (LBP) of
entire face is obtained. These LBPs are converted into
decimal number and then histograms of all those decimal
values are made. At the end, one histogram will be formed
for each images in the training data. Later, during recognition
process histogram of the face to be recognized is calculated
and then compared with the already computed histograms and
returns the best matched label associated with the student it
belongs to [9].
4. Attendance Updation
Fig.1. System Architecture
After face recognition process, the recognized faces will be
Typically this process can be divided into four stages, marked as present in the excel sheet and the rest will be
1. Dataset Creation marked as absent and the list of absentees will be mailed to
Images of students are captured using a web cam. Multiple the respective faculties. Faculties will be updated with
images of single student will be acquired with varied gestures monthly attendance sheet at the end of every month.
and angles. These images undergo pre-processing. The
images are cropped to obtain the Region of Interest (ROI) IV. RESULTS AND DISCUSSIONS
which will be further used in recognition process. Next step is The users can interact with the system using a GUI. Here
to resize the cropped images to particular pixel position. Then users will be mainly provided with three different options
these images will be converted from RGB to gray scale such as, student registration, faculty registration, and mark
images. And then these images will be saved as the names of attendance. The students are supposed to enter all the
respective student in a folder. required details in the student registration form. After
2. Face Detection clicking on register button, the web cam starts automatically
Face detection here is performed using Haar-Cascade and window as shown in Fig.3. pops up and starts detecting
Classifier with OpenCV. Haar Cascade algorithm needs to be the faces in the frame. Then it automatically starts clicking
trained to detect human faces before it can be used for face photos until 60 samples are collected or CRTL+Q is pressed.
detection. This is called feature extraction. The haar cascade These images then will be pre-processed and stored in
training data used is an xml file- training images folder.
haarcascade_frontalface_default. The haar features shown in The faculties are supposed to register with the respective
Fig.2. will be used for feature extraction. course codes along with their email-id in the faculty
registration form provided. This is important because the list
of absentees will be ultimately mailed to the respective
faculties.

Fig.2. Haar Features

IJERTV9IS050861 www.ijert.org 1191

(This work is licensed under a Creative Commons Attribution 4.0 International License.)
Published by : International Journal of Engineering Research & Technology (IJERT)
http://www.ijert.org ISSN: 2278-0181
Vol. 9 Issue 05, May-2020

V. CONCLUSION
This system aims to build an effective class attendance
system using face recognition techniques. The proposed
system will be able to mark the 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.
REFERENCES
[1] ttps://www.researchgate.net/publication/326261079_Face_detection_
system_for_attendance_of_class’_students
[2] Hapani, Smit, et al. "Automated Attendance System Using Image
Processing." 2018 Fourth International Conference on Computing
Communication Control and Automation (ICCUBEA). IEEE, 2018.
Fig.3. Face Detection [3] Akbar, Md Sajid, et al. "Face Recognition and RFID Verified
Attendance System." 2018 International Conference on Computing,
Electronics & Communications Engineering (iCCECE). IEEE, 2018.
In every session, respective faculty must enter their course [4] Okokpujie, Kennedy O., et al. "Design and implementation of a
code. Then after submitting the course code, the camera will student attendance system using iris biometric recognition." 2017
start automatically. The Fig.4. shows the face recognition International Conference on Computational Science and
window where two registered students are recognized and if Computational Intelligence (CSCI). IEEE, 2017.
[5] Rathod, Hemantkumar, et al. "Automated attendance system using
in case they were not registered it would have shown machine learning approach." 2017 International Conference on
‘unknown’. By pressing CTRL+Q, the window will be closed Nascent Technologies in Engineering (ICNTE). IEEE, 2017.
and attendance will be updated in the excel sheet and names [6] Siswanto, Adrian Rhesa Septian, Anto Satriyo Nugroho, and
of absentees will be mailed to the respective faculty. Maulahikmah Galinium. "Implementation of face recognition
algorithm for biometrics based time attendance system." 2014
International Conference on ICT For Smart Society (ICISS). IEEE,
2014.
[7] Lukas, Samuel, et al. "Student attendance system in classroom using
face recognition technique." 2016 International Conference on
Information and Communication Technology Convergence (ICTC).
IEEE, 2016.
[8] https://becominghuman.ai/face-detection-using-opencv-with-haar-
cascade-classifiers-941dbb25177
[9] https://www.superdatascience.com/blogs/opencv-face-recognition
[10] Salim, Omar Abdul Rhman, Rashidah Funke Olanrewaju, and Wasiu
Adebayo Balogun. "Class attendance management system using face
recognition." 2018 7th International Conference on Computer and
Communication Engineering (ICCCE). IEEE, 2018.

Fig.4. Face Recognition

Fig.5. Attendance sheet

The Fig.5. shows the attendance sheet updated after

recognition process. Recognized students are marked as ‘1’
and absent students are marked as ‘0’. The list of absentees
will be mailed to the respective faculty email-id.

IJERTV9IS050861 www.ijert.org 1192

(This work is licensed under a Creative Commons Attribution 4.0 International License.)