FACE RECOGNITION BASED ATTENDANCE MONITORING

SYSTEM USING PYTHON

Abstract: In the changing world, automatic facial recognition (AFR) systems have made several
advancements. Smart Attendance with Real-Time Face Recognition is a practical approach for
managing student attendance systems on a daily basis. Face recognition-based attendance
system is a mechanism that uses high-definition camera recording and other information
technologies to recognize a student's face for the purpose of taking attendance. In my facial
recognition project, a computer machine would be able to find and recognize human faces in
photographs or videos taken by a webcam quickly and accurately. For improving the efficiency of
face recognition, several algorithms and techniques have been developed, but the principle to be
applied here is openCV (Opensource Computer Vision), Python, and the tkinter GUI interface. It aids in
the translation of video frames into photographs so that the student's face can be easily identified for
attendance purposes and the attendance record can be easily updated.

INTRODUCTION
These days, technology strives to impart a vast amount of knowledge-based scientific advances.
Deep Learning is an intriguing area that allows a computer to train itself using datasets as input
and then have a suitable output during training using various learning algorithms. Nowadays,
attendance is regarded as a critical consideration for both students and teachers in educational
institutions. Through the advent in deep learning technologies, the computer can now
automatically detect the students' attendance results and keep a record of it. In general, the
attendance system of the student can be maintained in two different forms namely,
Manual Attendance System (MAS)
Automated Attendance System (AAS).
Manual Student Attendance Management is a method in which a teacher in charge of a single
subject must manually call the students' names and record their attendance. Manual
attendance will be seen as a time-consuming operation, and it is possible that the teacher may
forget someone, or that students may react to the absence of their friends several times. As a
result, the issue emerges when we consider the conventional method of taking attendance in
the classroom. We use an Automatic Attendance System to address all of these problems (AAS).
The Automated Attendance System (AAS) is a mechanism that uses face recognition
technologies to automatically predict a student's presence or absence in the classroom. It's also
possible to detect whether a student is asleep or awake during a class, and it can be used in
exam sessions to verify that the student is there. The location of students can be calculated by
filming their faces on a high-definition display video streaming service, making it very accurate
for the computer to recognize all of the students in the classroom. The two common Human Face
Recognition techniques are,  Feature-based approach  Brightness-based approach

The feature-based approach, also known as a local face recognition system, is used to pick out
main features of the face such as the eyes, ears, nose, lips, corners, and so on, while the
brightness-based approach, also known as a global face recognition system, is used to recognize
all of the image's components.
Existing Recognition System:
1. Fingerprint Based recognition system:
A portable fingerprint device must be calibrated with the students fingerprint prior to
using the current fingerprint-based attendance system. The student must record the
fingerprint on the configured computer later, either during lecture hours or before, to
ensure their attendance for the day. The concern with this method is that it can divert
students' attention away from the lesson.
2. RFID(Radio Frequency Identification) Based recognition system:
The student must take a Radio Frequency Identity Card with them and put it on the card reader
to register their attendance for the day in the RFID-based current scheme. The machine will bind
to RS232 and save the attendance information to a database. There is a chance that illegal
access could occur. Any students may use another student's ID to guarantee their attendance
when that student is unavailable, or they may even attempt to abuse it.
3. Iris Based Recognition System:
The pupil must stand in front of a monitor in order for the Iris-based student attendance
scheme to work. The student's iris will be scanned by the camera. The iris scan is
compared to the student's data in the database, and the attendance on their
participation must be changed. This lowers the institute's faculty member's paper and
pen workload. Which also aims to keep student data confidential by reducing the
likelihood of proxies in the classroom. It is a wireless biometric technique that addresses
the issue of bogus attendance as well as the difficulty of setting up the required
network.
4. Face Based Recognition System:
Facial recognition technology can be used to monitor attendance by using a high-
resolution digital camera to identify and recognize students' faces, and then comparing
the recognized face to students' face images saved in a database. The attendance is
identified in the attendance database for further computation until the student's face is
aligned with the stored photograph. If the caught image does not complement the face
of a student already in the database, it is saved as a new image in the database. There is
a chance that the camera will not catch the image correctly with this method, or that it
will skip any of the pupils.

Proposed Work and Methodology:

The proposed system's goal is to catch each student's face and archive it in a database for their
attendance. The student's face must be captured in such a way that all of the features of the
student's face are detected. The instructor does not need to physically take attendance in class
because the machine captures a recording, and the face is remembered and the attendance
database is checked by more processing steps. Python opencv was used to build this
framework.
when we run main.py face recognition based attendance system application is opened and
upon registering with the name and id in registration form, those are stored in student details
folder and images are stored in Training Image folder. Password security system is also enabled
for the application.

Advantages:
 It is one of the simplest algorithms for face recognition.
 The local features of the images can be characterized by this algorithm.
 Using this algorithm, considerable results can be obtained.

OpenCV: OpenCV (Open Source Computer Vision Library) is a library of programming functions
mainly aimed at real-time computer vision. Originally developed by Intel, it was later supported
by Willow Garage then Itseez (which was later acquired by Intel). The library is cross platform
and free for use under the open-source BSD license. Python is dynamically typed and garbage
collected. It supports multiple programming paradigms, including structured (particularly,
procedural), object-oriented, and functional programming. Python is often described as a
"batteries included" language due to its comprehensive standard library.

Tkinter : Tkinter is the standard GUI library for Python. Python when combined

with Tkinter provides a fast and easy way to create GUI applications. Tkinter provides a
powerful object-oriented interface to the Tk GUI toolkit. Import the Tkinter module.

Image Capture: We need some HD camera in order to get results. We can capture the images
from the video stream or by capturing each and every image from the webcam manually.

RESULTS:

First and foremost, we must add the person to the database. To do so, we'll need to
store his or her name and registered number.

Now we need to get pictures of the people from the webcam or some other available
cameras, such as the Laptop webcam we used here. Select the camera from which we
will take the picture and turn it on. The camera is plotted on the axis, and we can take
pictures and store them in the folder that is automatically generated with the registered
number we entered. The information is then saved in a folder. Let's take a picture of the
webcam and see what happens. The camera begins and takes a picture so that the
results can be checked against the archive that has been stored.
 Conclusion:
Capturing photographs with a webcam or a cc camera and applying facial detection and
recognition techniques will reduce human manual labor and improve security protection
by making decisions based on the recognition results. Face detection and recognition
can be used to incorporate a variety of applications, including automated attendance
systems focused on face recognition, worker attendances, protection, and safety, as well
as police applications such as detecting a suspect in a picture that aids in the capture of
a thief. We also introduced an attendance scheme for a lecture, section, or laboratory in
this system, in which the lecturer or teaching assistant keeps track of the students'
attendance. It saves time and effort, particularly if there are a large number of students
in the class. This attendance system demonstrates the use of facial recognition
technology for the purposes of student attendance, and this student record will be used
in exam-related problems in the future.

References:
[1] A Study of Various Face Detection Methods , Ms.Varsha Gupta1 , Mr. Dipesh Sharma2,ijarcce
volume 3https://www.ijarcce.com/upload/2014/may/IJAR CCE7G%2 0%20a%20varsha%20A
%20Study%20of%20Vario us%20F

[2]Face Recognition Based on HOG and Fast PCA Algorithm Xiang-Yu Li(&) and Zhen-Xian Lin.

[3]Attendance System Using Face Recognition and Class Monitoring System, Arun Katara1, Mr.
Sudesh2, V.Kolhe3http://www.ijritcc.org/download/browse/ Volume_
5_Issues/February_17_Volume_5_Issue_2/14895658 66_ 1503-2017.pdf

[4] G. Yang and T. S. Huang, “Human face detection in complex background,” Pattern
Recognition Letter, vol. 27, no.1, pp. 53-63, 1994.

[5] C. Kotropoulos and I. Pitas, “Rule-based face detection in frontal views,” Proc. Int’l Conf.
Acoustics, Speech and Signal Processing, vol. 4, pp. 2537-2540, 1997.

[6] Xinjun Ma, Hongqiao Zhang, XinZang, “A face detection algorithm based on modified skin-
color model”, CCC, vol. 1, pp. 3896-3900, IEEE, 2013

[7] V. Shehu and A. Dika, “Using Real Time Computer Algorithms in Automatic Attendance
Management Systems.” IEEE, pp. 397 – 402, Jun. 2010.

[8] Prof. P.K Biswas, Digital Image Processing

[9] M. A. Turk and A. P. Pentland, “Face Recognition Using Eigenfaces”in Proc. IEEE Conference
on Computer Vision and Pattern Recognition, pp. 586– 591. 1991
[10] W. Zhao, R. Chellappa, P. J. Phillips, and A. Rosenfeld, “Face recognition: A literature
survey,” ACM Computing Surveys, 2003, vol. 35, no. 4, pp. 399-458