International Journal of Engineering and Advanced Technology (IJEAT)

ISSN: 2249 – 8958, Volume-8, Issue-3S, February 2019

Face Recognition Based Attendance System

Nandhini R, Duraimurugan N, S.P.Chokkalingam 

ABSTRACT--- Automatic face recognition (AFR) technologies Automated Attendance System (AAS) is a process to
have made many improvements in the changing world. Smart automatically estimate the presence or the absence of the
Attendance using Real-Time Face Recognition is a real-world student in the classroom by using face recognition
solution which comes with day to day activities of handling
technology. It is also possible to recognize whether the
student attendance system. Face recognition-based attendance
system is a process of recognizing the students face for taking student is sleeping or awake during the lecture and it can
attendance by using face biometrics based on high - definition also be implemented in the exam sessions to ensure the
monitor video and other information technology. In my face presence of the student. The presence of the students can be
recognition project, a computer system will be able to find and determined by capturing their faces on to a high-definition
recognize human faces fast and precisely in images or videos that monitor video streaming service, so it becomes highly
are being captured through a surveillance camera. Numerous
reliable for the machine to understand the presence of all the
algorithms and techniques have been developed for improving
the performance of face recognition but the concept to be students in the classroom. The two common Human Face
implemented here is Deep Learning. It helps in conversion of the Recognition techniques are,
frames of the video into images so that the face of the student can  Feature-based approach
be easily recognized for their attendance so that the attendance  Brightness-based approach.
database can be easily reflected automatically. The Feature-based approach also known as local face
Keywords: Face recognition, Face detection, Deep Learning,
recognition system, used in pointing the key features of the
Convolution Neural Network(CNN).
face like eyes, ears, nose, mouth, edges, etc., whereas the
INTRODUCTION brightness-based approach also termed as the global face
recognition system, used in recognizing all the parts of the
The technology aims in imparting a tremendous image.
knowledge oriented technical innovations these days. Deep
Learning is one among the interesting domain that enables
LITERATURE SURVEY:
the machine to train itself by providing some datasets as
input and provides an appropriate output during testing by 2.1 A Counterpart Approach to Attendance and Feedback
applying different learning algorithms. Nowadays System using Machine Learning Techniques:
Attendance is considered as an important factor for both the In this paper, the idea of two technologies namely Student
student as well as the teacher of an educational organization. Attendance and Feedback system has been implemented
With the advancement of the deep learning technology the with a machine learning approach. This system
machine automatically detects the attendance performance automatically detects the student performance and maintains
of the students and maintains a record of those collected the student's records like attendance and their feedback on
data. the subjects like Science, English, etc. Therefore the
In general, the attendance system of the student can be attendance of the student can be made available by
maintained in two different forms namely, recognizing the face. On recognizing, the attendance details
 Manual Attendance System (MAS) and details about the marks of the student is obtained as
 Automated Attendance System (AAS). feedback.
Manual Student Attendance Management system is a
2.2 Automated Attendance System Using Face
process where a teacher concerned with the particular
Recognition:
subject need to call the students name and mark the
attendance manually. Manual attendance may be considered Automated Attendance System using Face Recognition
as a time-consuming process or sometimes it happens for the proposes that the system is based on face detection and
teacher to miss someone or students may answer multiple recognition algorithms, which is used to automatically
times on the absence of their friends. detects the student face when he/she enters the class and the
So, the problem arises when we think about the traditional system is capable to marks the attendance by recognizing
process of taking attendance in the classroom. To solve all him. Viola-Jones Algorithm has been used for face detection
these issues we go with Automatic Attendance which detect human face using cascade classifier and PCA
System(AAS). algorithm for feature selection and SVM for classification.
When it is compared to traditional attendance marking this
system saves the time and also helps to monitor the students.
2.3 Student Attendance System Using Iris Detection:
Revised Manuscript Received on February 14, 2019.
D. Viji Assistant Professor, Department of Computer Science and In this proposed system the student is requested to stand
Engineering, SRM IST, Chennai, Tamil Nadu, India. (E-mail:
[email protected])
Abhijith Shankar UG Student Department of Computer Science and
Engineering, SRM IST, Chennai, Tamil Nadu, India. (E-mail:
[email protected])

Published By:
Blue Eyes Intelligence Engineering
Retrieval Number: C11230283S19/19©BEIESP 574 & Sciences Publication
 FACE RECOGNITION BASED ATTENDANCE SYSTEM

in front of the camera to detect and recognize the iris, for camera that detects and recognizes the faces of the students
the system to mark attendance for the student. Some and the machine compares the recognized face with
algorithms like Gray Scale Conversion, Six Segment students’ face images stored in the database. Once the face
Rectangular Filter, Skin Pixel Detection is being used to of the student is matched with the stored image, then the
detect the iris. It helps in preventing the proxy issues and it attendance is marked in attendance database for further
maintains the attendance of the student in an effective calculation. If the captured image doesn't match with the
manner, but in one of the time-consuming process for a students' face present in the database then this image is
student or a staff to wait until the completion of the previous stored as a new image onto the database. In this system,
members. there are possibilities for the camera to not to capture the
image properly or it may miss some of the students from
2.4 Face Recognition-based Lecture Attendance System:
capturing.
This paper proposes that the system takes the attendance
automatically recognition obtained by continuous PROPOSED SYSTEM:
observation. Continuous observation helps in estimating and
The task of the proposed system is to capture the face of
improving the performance of the attendance. To obtain the
each student and to store it in the database for their
attendance, positions and face images of the students present
attendance. The face of the student needs to be captured in
in the class room are captured. Through continuous
such a manner that all the feature of the students' face needs
observation and recording the system estimates seating
to be detected, even the seating and the posture of the
position and location of each student for attendance
student need to be recognized. There is no need for the
marking. The work is focused on the method to obtain the
teacher to manually take attendance in the class because the
different weights of each focused seat according to its
system records a video and through further processing steps
location. The effectiveness of the picture is also being
the face is being recognized and the attendance database is
discussed to enable the faster recognition of the image.
updated.
EXISTING RECOGNITION SYSTEMS:
RESULTS & DISCUSSIONS
3.1 Fingerprint Based recognition system: The main working principle of the project is that, the
In the Fingerprint based existing attendance system, a video captured data is converted into image to detect and
portable fingerprint device need to be configured with the recognize it. Further the recognized image of the student is
students fingerprint earlier. Later either during the lecture provided with attendance, else the system marks the
hours or before, the student needs to record the fingerprint database as absent.
on the configured device to ensure their attendance for the
day. The problem with this approach is that during the
lecture time it may distract the attention of the students.
3.2 RFID(Radio Frequency Identification) Based
recognition system:
In the RFID based existing system, the student needs to
carry a Radio Frequency Identity Card with them and place
the ID on the card reader to record their presence for the
day. The system is capable of to connect to RS232 and
record the attendance to the saved database. There are
possibilities for the fraudulent access may occur. Some are
students may make use of other students ID to ensure their
presence when the particular student is absent or they even
try to misuse it sometimes.
3.3 Iris Based Recognition System:
Figure 1.1
In the Iris based student attendance system, the student
needs to stand in front of a camera, so that the camera will
scan the Iris of the student. The scanned iris is matched with 5.1 Capture video:
data of student stored in the database and the attendance on The Camera is fixed at a specific distance inside a
their presence needs be updated. This reduces the paper and classroom to capture videos of the frontal images of the
pen workload of the faculty member of the institute. This entire students of the class.
also reduces the chances of proxies in the class, and helps in
5.2 Separate as frames from the video:
maintaining the student records safe. It is a wireless
biometric technique that solves the problem of The captured video needs to be converted into frames per
spurious attendance and the trouble of laying the second for easier detection and recognition of the students'
corresponding network.
3.4 Face Based Recognition System:
The facial recognition technology can be used in
recording the attendance through a high-resolution digital

Published By:
Blue Eyes Intelligence Engineering
Retrieval Number: C11230283S19/19©BEIESP 575 & Sciences Publication
 International Journal of Engineering and Advanced Technology (IJEAT)
ISSN: 2249 – 8958, Volume-8, Issue-3S, February 2019

face to generate the attendance database.

Figure 1.5

NETWORK DIAGRAM:
Figure 1.2 A CNN (Convolution Neural Network) uses a system like
a multilayer perceptron that has been designed to process the
5.3 Face Detection:
requirements faster. The CNN layer consist of an input
Face Detection is the process where the image, given as layer, an output layer and a hidden layer that includes
an input (picture) is searched to find any face, after finding multiple convolution layers, pooling layers, fully connected
the face the image processing cleans up the facial image for layers, and normalization layers. The removal of limitations
easier recognition of the face.CNN algorithm can be and increase in efficiency for image processing results in a
implemented to detect the faces. system that is far more effective, simpler to trains limited for
image processing and natural language processing.

Figure 1.3

5.4 Face Recognition:

After the completion of detecting and processing the face,
it is compared to the faces present in the students' database CONCLUSION:
to update the attendance of the students. Thus, the aim of this paper is to capture the video of the
students, convert it into frames, relate it with the database to
ensure their presence or absence, mark attendance to the
particular student to maintain the record. The Automated
Classroom Attendance System helps in increasing the
accuracy and speed ultimately achieve the high-precision
real-time attendance to meet the need for automatic
classroom evaluation.

FUTURE ENHANCEMENTS:
 Automated Attendance System can be implemented in
larger areas like in a seminar hall where it helps in
Figure 1.4 sensing the presence of many people.
 Sometimes the poor lighting condition of the
5.5 Post-Processing: classroom may affect image quality which indirectly
The post-processing mechanism involves the process of degrades system performance, this can be overcome in
updating the names of the student into an excel sheet. The the latter stage by improving the quality of the video
excel sheet can be maintained on a weekly basis or monthly or by using some
basis to record the students' attendance. This attendance algorithms
record can be sent to parents or guardians of students to
report the performance of the student.

Published By:
Blue Eyes Intelligence Engineering
Retrieval Number: C11230283S19/19©BEIESP 576 & Sciences Publication
 FACE RECOGNITION BASED ATTENDANCE SYSTEM

REFERENCES:
1. N.Sudhakar Reddy, M.V.Sumanth, S.Suresh Babu, "A
Counterpart Approach to Attendance and Feedback System
using Machine Learning Techniques",Journal of Emerging
Technologies and Innovative Research (JETIR), Volume 5,
Issue 12, Dec 2018.
2. Dan Wang, Rong Fu, Zuying Luo, "Classroom Attendance
Auto-management Based on Deep Learning",Advances in
Social Science, Education and Humanities Research, volume
123,ICESAME 2017.
3. Akshara Jadhav, Akshay Jadhav, Tushar Ladhe, Krishna
Yeolekar, "Automated Attendance System Using Face
Recognition", International Research Journal of Engineering
and Technology (IRJET), Volume 4, Issue 1, Jan 2017.
4. B Prabhavathi, V Tanuja, V Madhu Viswanatham and M
Rajashekhara Babu, "A smart technique for attendance system
to recognize faces through parallelism", IOP Conf. Series:
Materials Science and Engineering 263, 2017.
5. Prajakta Lad, Sonali More, Simran Parkhe, Priyanka Nikam,
Dipalee Chaudhari, " Student Attendance System Using Iris
Detection", IJARIIE-ISSN(O)-2395-4396, Vol-3 Issue-2
2017.
6. Samuel Lukas, Aditya Rama Mitra, Ririn Ikana Desanti, Dion
Krisnadi, "Student Attendance System in Classroom Using
Face Recognition Technique", Conference Paper DOI:
10.1109/ICTC.2016.7763360, Oct 2016.
7. K.Senthamil Selvi, P.Chitrakala, A.Antony Jenitha, "Face
Recognition Based Attendance Marking System", IJCSMC,
Vol. 3, Issue. 2, February 2014.
8. Yohei KAWAGUCHI, Tetsuo SHOJI, Weijane LIN, Koh
KAKUSHO, Michihiko MINOH, "Face Recognition-based
Lecture Attendance System", Oct 2014.
9. Shireesha Chintalapati, M.V. Raghunadh, "Automated
Attendance Management System Based On Face Recognition
Algorithms", IEEE International Conference on
Computational Intelligence and Computing Research, 2013.
10. B. K. Mohamed and C. Raghu, “Fingerprint attendance
system for classroom needs,” India Conference (INDICON),
Annual IEEE, pp. 433–438, 2012.

Published By:
Blue Eyes Intelligence Engineering
Retrieval Number: C11230283S19/19©BEIESP 577 & Sciences Publication