Face Recognition Attendance System

Ravindra Nath1 , Anuj Saroj2 , Rishi Maurya3 , Suryanarayan4

1
rnkatiyar@gmail.com, 2 sarojanuj213@gmail.com,
3
rishimaurya893@gmail.com, 4 suryanarayanbaijpur@gmail.com

Abstract
This research paper provides an in-depth exposition on the construction of a
face recognition attendance system. The proposed system intends to automate
the attendance task through utilizing different techniques of facial recognition to
recognize and verify registered individuals. The system uses a camera to capture
images of individuals, and the collected data is processed and analyzed with a vari-
ety of image processing techniques to extract facial characteristics. The extracted
characteristics are then compared with the existing base to verify the individual’s
identity. The system generates attendance reports notifying teachers or managers
to monitor, and manage, attendance accordingly in real-time. The paper mentions
the approach and experiments set up, the images processing techniques used and
the algorithms applied to reach the objective. The experimental results indicate the
feasibility and potential success of the system at respectively identifying individual
faces and generating attendances automatically. Finally, the paper highlights the
benefits of an automated face recognition attendance system, such as time-saving,
error reduction, and management possibilities for attendance in organizations.
Keywords: Face Recognition, Attendance Management System, Haar
Cascade, Open CV.

I. Introduction
The face recognition attendance system being proposed leverages modern computer vision
and machine learning methods to recognize and verify identifying individuals through
facial recognition. The proposed system uses a camera to capture images of individuals,
and the captured information is processed through many image processing methods to
recognize and then model facial images. The facial models are used to verify the identity of
each individual, and then attendance is effectively captured in a collection. The proposed
system would effectively be available in real time and able to provide reports and allows
teachers or managers to track attendance effortlessly. The research study outlined here
would provide detailed descriptions of the proposed face recognition attendance system
and will add on to the proposed advantages of the new system in relation to attending
methods compared to the old. Afterwards the paper will elaborate examining the methods
and descriptions the methods use in deep learning algorithms to develop this system. The
research will gather performance data and longterm usage data while exploring the ability
to monitor facial expressions while attending, and the impact of lighting or shadows over
face recognition. In the end, the study will consider other applications of a proposed facial
recognition attendance system for various settings such as classrooms and workplaces,
while considering benefits affecting everyone.

1
 II. Paper Studies
Numerous investigations have been undertaken into the implementation of facial recogni-
tion technology as a component of attendance systems. For example, a study by Zhang et
al. (2018) suggested a facial recognition attendance system that incorporated deep learn-
ing and artificial intelligence algorithms. The study employed a convolutional neural
network (CNN) model to identify recognized facial images, achieving a recorded accuracy
of 97.5on a dataset of 600 facial images.[4]
Moreover, Malyala et al. (2019) also presented a hybrid approach to attendance man-
agement based on the utilization of RFID and facial [[recognition technologies.[6] In this
system, RFID tags recorded attendance, but facial recognition verified the identity of
individuals, thus reducing errors and preventing fraud.
Similarly, Lee et al. (2019) implemented a facial recognition attendance system that used
a smartphone camera and cloud-based architecture. The study concluded successfully
demonstrating that the system operated with high accuracy confirming abnormal atten-
dance circumstances, and provided real-time attendance records monitoring.[2]
In addition, Intharawijitr et al. (2019) presented an extensive assessment of various face
recognition algorithms including Eigenface, Fisherface, and Local Binary Patterns His-
togram frame alerts (LBPH) in attendance systems indicating that LBPH provided the
most accurate results with high efficiency in a facial recognition attendance system.
The above studies of the literature effectively highlight the considerable potential of fa-
cial recognition technology in attendance management systems. In addition, these studies
suggest that facial recognition technologies are effective not only at identifying individu-
als but also provide an effective, fast, reliable, and secure approach to manage attendance
data.[5]

III. Techniques
A face recognition attendance system generally comprises a number of techniques and
methodologies that are exploited to have accurate and efficient face recognition for at-
tendance tracking. Following are some of the common techniques used in such systems:

III.a Face Detection

Face detection attendance system heavily relies on the use of trustable techniques such as
Haar Cascades and Histogram of Oriented Gradients (HOG) in detecting faces. Real time
face detection is made possible by Haar Cascades; this is because, a number of cascading
classifiers which have been trained using both positive and negative image samples are
utilized. This method works efficiently and quickly borderlining on instantaneous, which
makes it useful for keeping track of live attendance.[6] Whereas HOS also known as HOG
is in Many parts about orientation, especially in how gradients are oriented within certain
areas of an image, this helps to improve the definition of facial structures. When used
together, however, these methods form an excellent system for face detection regardless
of the lighting and posture conditions of the head, thereby making it possible to identify
all of the participants and register their attendance.

2
III.a.a Haar Cascade Algorithm
It is an object detection system that can recognize faces in still photos or videos in
motion. To impute a person, faces guardians Haars cascade classifiers are trained on a
huge number of images with faces and without faces. This means in place of labeling
non-facial regions, waist up haar classifiers look around the window for faces. Studies
indicate that it is almost impossible to develop a reliable system that would perform skin
color segmentation of human faces. One application of the Haar Cascade Algorithm is
face detection, people detection, object detection and detection of facial expressions for a
given image. In fraction of time, given picture, the Haar Cascade Classifier is considered
to be one of the most efficient and accurate face detection system.[9] The essential part
of the face detection Haar Cascade Classifier is Haar features. Figure shows what the
Haar Cascade Classifier is capable of, which is any object, although it is intended that
these features are used to identify if a feature exists in an image or not. They operate
and concentrate on exact eye-centre localization with a scope on a laptop screen. Five
different procedures were used within the research. The following figure depicts the study
of Viola and Jones. This machine learning approach derives a cascade function by using a
training set containing both positive and negative images in appropriate proportions. In
that case, it is used to locate objects in other images. Therefore, to enhance classification
performance, this research study has integrated the use of a lot of positive picture sets
(pictures with faces), and a great amount of negative picture sets (pictures without faces).
Therefore, I am expected to perfrom feature extraction on this. In accordance with Soo,
“A Haar-like feature examines adjacent rectangular zones in a specific position within
a detection window, sums the pixel values in each area and then finds the difference
between these sums.”[9]

Figure 1: Haar Cascade

III.b Face Recognition

An attendance system that utilizes face detection incorporates various face recognition
techniques for the reliable identification of individuals. Eigenfaces and Fisherfaces are two

3
of such methods that apply statistical techniques to model and compare facial appear-
ances, which enhances recognition from pixel values using principal component analysis
and class separability.[9] In addition to these, more complex deep learning models such as
FaceNet make use of convolutional neural networks to create embeddings in high dimen-
sions, and hence identification is possible even with different variations. Such methods,
frequently embedded with support vector machines for classification purposes, further
improve the timeliness and accuracy of the attendance management systems by enabling
matching of a person’s face with already saved database images of registered individuals.

III.c Data Preprocessing

System to mark attendance through face detection incorporates important data prepro-
cessing methods like image normalization and face alignment which greatly improves the
rate of recognition. Image normalization refers to the scale or adjustment of pixel values
of images so as to adjust for the lighting or the contrast, hence helps in facial features
improvement under different conditions.[11] Face alignment, in turn, guarantees proper
orientations and scalings of facial images through the alignment of crucial key landmarks,
for instance, eyes and mouth. Although mouths and eyes may differ in shapes across dif-
ferent people, a certain degree of uniformity is achieved with respect to all the parameters
that allow their imaging to detangle from the ideal detection and recognition algorithms.
With these preprocessing methods, the system allows for better and reliable precision
when tracking attendance.

III.d Feature Extraction

In the attendance system utilizing face detection, the auxiliary algorithms such as Local
Binary Pattern (LBP) and deep feature extraction play their role for the correct iden-
tification.[13] LBP provides an analysis of the local texture by making a comparison of
the pixel in each position and the neighbouring pixels thus forming a strong description
of a facial region which does not change with light. On the other hand, deep feature ex-
traction is based on convolutional neural networks (CNN) where the system captures and
learns multi-level features that are embedded in the input raw images, therefore, enabling
recognition of faces that vary in structure and with many deliverables. Therefore these
approaches are integrated into the system in order to make it more efficient in detecting
and recognizing different people thus improving the management of attendance.

III.e Attendance Management

Face detection attendance system involves a reliable database and user interface tech-
nology for management of attendance. Due to the inclusion of a structured database
containing their user profiles, attendance history and facial embeddings, this makes it
easier to retrieve and modify entries within a short time. The user interface, which
allows for ease of use to the administrators, is equipped with dash boards and search
functions that help manage attendance reports and profiles respectively without any has-
sle. All in all, these elements promote the correct recording and simple management of
attendance logs.

4
III.f Real-Time Processing
In an attendance systems that employs face detection, it is necessary touse real time
processing techniques so that attendance records can be updated on the go. Optimized
algorithms such as Haar extending and YOLO are employed for fast face detection in
a video. Computation speed is enhanced through the use of Graphics Processing Units
(GPUs), while buffering and parallel processing reducing the latency in data researched
methods. These methods make it possible to take attendance and log the information at
once enhancing the smoothness of user interaction.[6]

IV. Results

Figure 2: Opening Interface

The system’s initial interface looks like this. Once the program is executed success-
fully, this GUI will be displayed. The lower part of the image displays the different
icons/buttons along with its functioning name. Clicking the particular button will open
another GUI window performing specialized task. As we can see, here total of 8 buttons
are used . You can add more if you want. This is all designed using the Tkinter library
in python.

Figure 3: Student Details Button Window

Upon pressing the student details button on botom page opening this media will be dis-
played. Here different entry fields and combo boxes are observed. The details which
needs to be saved are typed here. There two radio buttons used for photos option which
means either you will take a photo or you will not. There are several operating buttons
at the left bottom of the window. Using this buttons we can save , update, delete and
reset all the details stored. The take option will activate a camera. It can be a web
camera or any integrated camera external to the device. The camera when opened will

5
automatically click 20 sample pictures of the same person. These pictures taken shall
go in a specific folder as .jpg images. All these will be gray scale images of the sample
pictures taken.

Figure 4: Photos Button Window

Below is shown the screenshot of the directory where stored image samples are kept. This
window can be opened and closed whenever the photos button found on the opening in-
terface is clicked.

Figure 5: Train Data Button Window

Upon clicking the ’Train Data’ option on the homepage, this window will pop up. The
pictures sample are forwarded to this window with the intent of training using the algo-
rithm.

Figure 6: Face Detector Button Window

When the window is opened, the open face detector button on the initial interface
will launch this particular window. A camera will be activated. The camera will look
for a face in order to detect it and if found will show the information of that person or
otherwise will show unknown.

6
 Figure 7: Attendance Button Window

If the individual is properly identified, attendance details are captured in a .csv format.
That file reflects the information in real-time. The file is also visible to the user through
a button called import csv where user can fill in the details that will be shown on the
screen’s extreme right side. The information, on the other hand, can be taken out using
an export csv button which will bring us at an interface where one would be able to
create an excel file.

Figure 8: Excel File view

Hence find the attached exported excel file that contains an attendance record for
every individual without any manual intervention to store the attendance status of the
individual.

Figure 9: Help Desk Button Window

7
 The screenshot demonstrates the Help Desk icon accessible on the home page. Here
the developer’s email is visible. One can use the same to drop a mail in case they
encounter any problems.

V. Analysis
The study of implementation of face detection based attendance system determines the
effectiveness, accuracy and efficiency of the system in real use cases. Performance metrics,
such as the recognition accuracy, processing speed of the system, and its tolerance levels
with respect to lighting, pose and occlusion changes, are considered. With the inclusion
of Haar Cascades for detection and deep learning models for recognition, the system can
attain high levels of accuracy. Furthermore, the ability to process information in real
time is very important so that attendance can be captured instantaneously which makes
the system useful in environments that require versatility and rapid movement such as a
classroom or a work station. It also entails the taking into consideration of user responses
and utilization of the system which are also important in moderating performance so as
to enhance enjoyment and effectiveness. Ultimately, these evaluations provide assurances
that the attendance system is optimally designed for ease of use and practicality for the
users.

VI. Conclusion
This project describes an automated student attendance system using facial recognition
technology. The proposed solution allows identification of people using attendance pho-
tographs collected at registration and matching with input photographs. The method
proposed identifies and detects faces using an input facial image taken from a clip of a
recorded video. Furthermore, it presents a means of vieweing the attendance records.
In recent years, with the advancement of digital technology, the turning out of facial
recognition based attendance management systems has increased as well as the touching
mounted in them in terms of their precision. In fact, its time consumption for processing
images is also appealing to the users. The use of facial recognition attendance systems
offers an extra layer of security in the workplace.

VII. Future Enhancement

Face detection attendance systems are poised for further improvements for instance re-
garding accuracy and versatility metrics with advancements in deep learning method-
ologies such as; transfer learning and Generative Adversarial Networks for better rep-
resentation of the features used. Performance of the system could also be improved in
situations of poor illumination by the inclusion of other modalities for example inte-
grating biometric information or using infrared cameras. Furthermore, the inclusion of
privacy-preserving strategies where processing occurs on device or data is anonymized
would help in alleviating the fears of data security of the users. Better Design of the
User interface for enhanced accessibility; boosting Real Time analytical features would
cumulatively enhance the User Experience, and enhance efficiency of the system across
different environments.

8
 References
[1] Smitha, Pavithra S Hegde, Afshin “Face Recognition based Attendance Management
System” in IJERT 2020.
[2] Prof. Priyanka Manke, Pawan Sakat, Mohammed Hamza Siddiqui, Qureshi Abdul
Qadir, Himanshu Pednekar “Facial Recognition-Based Attendance System” in re-
searchgate 2024. https://www.researchgate.net/publication/379985898
[3] Muhammad Haikal Mohd Kamil1, Norliza Zaini1, Lucyantie Mazalan1, Afiq Harith
“Online attendance system based on facial recognition with face mask detection” in
Springer 2023. https://doi.org/10.1007/s11042-023-14842-y
[4] Soundarya S. , Ashwini P. , Rucha W. , Gaurav K “ A Review Paper on Atten-
dance Management System Using Face Recognition” at IJCRT 2021. Department of
Information Technology.
[5] Shreyak Sawhney, Karan Kacker, Samayak Jain, Shailendra Narayan ,Rakesh Garg
“Real Time Smart Attendance system using face recognition techniques “ in in-
ternational conference on cloud computing data science and engineering 2019.
https://ieeexplore.ieee.org/abstract/document/877693 4
[6] Soundarya S1. , Ashwini P2. , Rucha W3. , Gaurav K4. MS.Savitri Patil Department
Of Information Technology G.H. Raisoni(GHRCEM) Pune,India
[7] Isha Rajput, Nahida Nazir, Navneet Kaur, Shashwat Srivastava, Abid Sarwar,
Baljinder Kaur, Omdev Dahiya, Shruti Aggrawal. Attendance Management System
using Facial Recognition, DOI: 10.1109/ICIEM54221.2022.9853048,17 August 2022
[8] Mazen Ismaeel Ghareb , Dyaree Jamal Hamid , Sako Dilshad Sabr , Zhyar Farih
Tofiq, New approach for Attendance System using Face Detection and Recognition,
DOI: 10.24271/psr.2022.161680, November 2022
[9] Miss. Rutuja Fasate, Dr. Kashmira Kasat, “Face Recognition Attendance System
Using Python” ISSN: 2320-2882 JCRT2306717 Issue 6 June 2023
[10] Ghalib Al-Muhaidhri , Javeed Hussain, Smart Attendance System using Face Recog-
nition , ISSN: 2278-0181 ,Vol. 8 Issue 12, December-2019
[11] Amrutha H. B, Anitha C, Channanjamurthy K. N, Raghu R, Attendance Monitoring
System Using Face Recognition, DOI : 10.17577/IJERTCONV6IS13213, 24-04-2018
[12] Chappra Swaleha,Ansari Salman, Shaikh Abubakar, Prof. Shrinidhi Gindi, Face
Recognition Attendance System Volume:04/Issue:04/April-2022
[13] Hajar Filali Jamal Riffi Adnane Mohamed Mahraz Hamid Tairi, Multiple face de-
tection based on machine learning, 978-1-5386-4396 9/18/31.00 c 2018 IEEE.
[14] Shubhobrata Bhattacharya, Gowtham Sandeep Nainala, Prosenjit Das and Au-
robinda Routray, Smart Attendance Monitoring System (SAMS): A Face Recog-
nition based Attendance System for Classroom Environment, 2018 IEEE 18th In-
ternational Conference on Advanced Learning Technologies, 2161- 377X/18/31.00
©2018 IEEE DOI 10.1109/ICALT.2018.00090.

9
[15] Aftab ahmed, Jiandong guo, Fayaz ali, Farha deeba, Awais ahmed, LBPH Based Im-
proved Face Recognition At Low Resolution, International Conference on Artificial
Intelligence and Big Data, 978-1-5386-6987 7/18/31.00 ©2018 IEEE.

[16] Hemantkumar Rathod, Yudhisthir Ware, Snehal Sane, Suresh Raulo, Vishal Pakhare
and Imdad A. Rizvi, Automated Attendance System using Machine Learning Ap-
proach, 2017 International Conference on Nascent Technologies in the Engineering
Field (ICNTE 2017), 978-1-5090-2794- 1/17/31.00 ©2017 IEEE.

[17] Poornima S1, Sripriya N2, Vijayalakshmi B3,Vishnupriya P4, Attendance Monitor-
ing System using Facial Recognition with Audio Output and Gender Classification,
IEEE International Conference on Computer, Communication, and Signal Process-
ing (ICCCSP-2017), 978-1-5090-3716-2/17/31.00 ©2017 IEEE.

[18] Jacky Efendi,Muhammad Ihsan Zul,Wawan Yunanto, Real Time Face Recognition
using Eigenface and Viola-Jones Face Detector, INTERNATIONAL JOURNAL ON
INFORMATICS VISUALIZATION ,Vol 1 (2017) NO 1,e-ISSN : 2549- 9904,ISSN :
2549-9610.

[19] ] A. Arjun Raj, M. Shoheb, K. Arvind and K. S. Chethan, ”Face Recognition Based
Smart Attendance System,” 2020 International Conference on Intelligent Engineering
and Management (ICIEM), London, UK, 2020, pp.

[20] H. Yang and X. Han, ”Face Recognition Attendance System Based on Real-Time
Video Processing,” in IEEE Access, vol. 8, pp. 159143-159150, 2020

[21] Edison Kagona and Sani Usman ”Student’s Attendance Management in higher in-
stitutions using azure cognitive service ad Open CV face detection and recognition
attendance system” Department of Computer Science and Information Technology,
Faculty of Science and Technology, International University of East Africa; P.O.Box
35502 Kampala.

[22] Smitha, Hegde, Pavithra and Afshin,. (2020). Face Recognition based Atten-
dance Management System. International Journal of Engineering Research and. V9.
10.17577/IJERTV9IS050861.

[23] Smitha, Hegde, Pavithra Afshin,. (2020). Face Recognition based Attendance
Management System. International Journal of Engineering Research and. V9.
10.17577/IJERTV9IS050861.

[24] OpenCv Documentation -https://opencv.org

[25] Numpy - https://numpy.org

10