Journal of Advanced Research in Applied Sciences and Engineering Technology 33, Issue 2 (2024) 198-208

Journal of Advanced Research in Applied

Sciences and Engineering Technology
Journal homepage:
https://semarakilmu.com.my/journals/index.php/applied_sciences_eng_tech/index
ISSN: 2462-1943

Streamlining Attendance Management in Education: A Web-Based

System Combining Facial Recognition and QR Code Technology
Emily Sing Kiang Siew1,*, Zhi Yan Chong1, Sah Nah Sze2, Richki Hardi3

1 Faculty of Computing and Software Engineering, i-CATS University College, Jalan Stampin Timur, 93350 Kuching, Sarawak, Malaysia
2
Faculty of Computer Science & Information Technology, Universiti Malaysia Sarawak, 94300 Kota Samarahan, Sarawak, Malaysia
3 Department of Informatics, Universitas Mulia, Balikpapan, Indonesia

ARTICLE INFO ABSTRACT

Article history: Attendance tracking has long posed challenges in educational institutions due to the
Received 26 August 2023 inefficiency and error-prone nature of traditional paper-based methods. In response,
Received in revised form 5 October 2023 many institutions have embraced web technologies and automated attendance
Accepted 16 October 2023 systems, incorporating biometrics, QR codes, barcodes, and RFID-based technologies.
Available online 2 November 2023
However, the applicability of these systems may vary across different educational
settings. This paper introduces a web-based student attendance management system
that combines facial recognition technology and QR codes to address the challenges
associated with manual attendance tracking in a university college. The system
leverages a centralized database for streamlined monitoring and auditing of
attendance records, offering the flexibility to choose between face recognition and QR
code attendance marking options. User acceptance tests were conducted to evaluate
the system's effectiveness, and the results indicate that the proposed system greatly
improves attendance tracking transparency and demonstrates high usability based on
positive user ratings. Additionally, the preference for face recognition over QR code
Keywords: scanning was evident. Incorporating these technologies into the automated
Attendance System; Web-Based; QR attendance system represents a substantial advancement in educational technology,
Code; Haar Cascade; LBPH offering an accurate and efficient way of recording attendance.

1. Introduction
1.1 Background

In the current academic system, regular attendance by students in classes plays a pivotal role in
assessing students' performance and measuring their participation in a course [1,2]. Moreover, in
certain institutions, attendance in a course is mandatory as a prerequisite for taking the exam. The
conventional manual student attendance system has been widely used in educational institutions for
many years. However, manually marking attendance using paper-based sheets and calling out names
can be a laborious and tedious task, especially in classrooms with a high teacher-to-student ratio. To
overcome challenges like impersonation, tampering with records, or signing in for absent friends, an

*
Corresponding author.
E-mail address: [email protected]

https://doi.org/10.37934/araset.33.2.198208

198
Journal of Advanced Research in Applied Sciences and Engineering Technology
Volume 33, Issue 2 (2024) 198-208

automated attendance system utilizing biometrics or QR codes can provide a more accurate, reliable,
and efficient method of tracking attendance. Implementing an automated attendance system with
difficult-to-falsify unique identifiers is essential to ensuring accurate student attendance records.
Similarly, at i-CATS University College, the institution currently employs a manual method for
recording student attendance. During class sessions, lecturers mark attendance by calling out
students' names or distributing paper-based attendance sheets. The recorded data is then manually
entered into predefined-format Excel files, with each lecturer maintaining their attendance data,
sheets, and absenteeism forms, which are later shared in printed copies. The manual attendance
system has limitations in digitizing attendance data, record-keeping, report generation, and sharing,
including inefficient data management, time-consuming tracking, and attendance inconsistencies.
In response to the limitations of traditional manual attendance systems and the demand for a
more efficient and dependable method of managing attendance data, this research is dedicated to
the design, development, and evaluation of a web-based student attendance management system
(WSAMS). The system leverages two methods for attendance tracking: facial recognition technology
and QR codes, which enhance students' engagement and interaction through the integration of
technology [3]. The primary focus of this study is to assess the effectiveness and user acceptance of
the proposed attendance management system, along with the incorporated technologies.

1.2 Related Works

Numerous automated student attendance systems based on face recognition have been
implemented in educational institutions. These systems utilize a camera to capture the faces of all
students simultaneously [4,5] or one by one [6,7].
Fuzail et al., [4] integrated a real-time face detection algorithm into an existing learning
management system on a web server using Pyfaces and Haar classifiers. Images of the students in
the class are captured at predetermined intervals by the camera, and the process continues until all
detected faces are identified or manually stopped. These captured images, with the corresponding
course code, are then sent to the server for face matching through the use of web services. However,
it was unable to accurately identify every individual student present in the class. Raghuwanshi and
Swami [5] developed a face recognition attendance system using Matlab and Excel that utilized
principle component analysis (PCA) and linear discriminant analysis (LDA)-based feature extraction.
They used a camera to capture all student faces in a classroom simultaneously to eliminate queuing
during the attendance process. However, the system reported low accuracy, with recognition rates
of only 53.33% and 60% for PCA and LDA, respectively.
Chintalapati and Raghunadh [6] proposed a standalone attendance system that utilized various
techniques, including PCA, LDA, and local binary pattern histograms (LBPH), along with several
classifiers for face recognition. The study concluded that LBPH outperformed both PCA and LDA
algorithms, achieving the highest recognition rate and the lowest false positive rate. Chinimilli et al.,
[7] presented a stand-alone attendance management system capable of generating Excel attendance
sheets. The system employed the Haar cascade and LBPH algorithms for face recognition. It achieved
a good face recognition rate with a low false-positive rate, using a small dataset and considering 3
feet as the ideal recognition distance.
QR (Quick Response) codes are two-dimensional codes that store large amounts of data in a
compact image and enable fast reading in all directions, up to 360 degrees [8]. Composed of black
and white rows and columns, QR codes can be easily scanned by a QR scanner or a smartphone with
a camera using a reader application, allowing for effortless decoding and storage of information in a
database [9, 10]. Due to their versatility and convenience, the implementation of QR code attendance

199
Journal of Advanced Research in Applied Sciences and Engineering Technology
Volume 33, Issue 2 (2024) 198-208

systems has gained popularity in the educational sector. Physical QR codes can be generated on cards
for each student [11], or digital QR codes can be generated by students using their smartphone app
[12]. In both cases, a QR scanner or scanning device is used to confirm attendance. Another approach
is for lecturers to generate digital QR codes [13,14], which can be either static or dynamic. Static QR
codes can be easily shared, leading to potential false attendance records. In contrast, dynamic QR
codes change frequently, making it difficult for students to deceive the system.
Facial recognition and QR codes exhibit promising potential in automated attendance systems,
offering an infrastructure-free solution by leveraging smartphones or computers with cameras. This
eliminates the necessity for physical cards or RFID devices. A noteworthy finding from a study [15],
which implemented an RFID-based attendance management system in a university, revealed that a
significant percentage of teachers (around 50%), spanning different age groups, showed little interest
in using the system despite being aware of its efficiency, opting for traditional methods instead.
Additionally, cases were observed where students brought RFID cards belonging to other students to
mark their attendance.
Many studies in the literature focus primarily on algorithm accuracy and technical aspects of
automated attendance recording, often overlooking crucial post-processing of attendance data,
which is essential for monitoring, auditing, managing absenteeism, and generating reports.
Furthermore, user preference, acceptance, and satisfaction with these technologies remain
underexplored. To address this gap, our study aims to develop a web-based attendance management
system using facial recognition and QR code technology. This system offers flexible options, reducing
hardware installation and long-term maintenance requirements, providing a cost-effective solution.
It highlights the importance of establishing the necessary technological infrastructure for educational
institutions, considering factors such as internet connectivity, hardware, platforms, and staff
competence, tailored to the institution's capacity [16].
While much of the reviewed literature used standalone systems, our preference is a web-based
system due to its advantages: rapid data access, scalability, responsiveness, interactivity, remote
management, and centralized data. According to Davis [17], users' behavioural intentions to use the
system are significantly influenced by their perception of its usefulness and ease of use. Nugroho and
Fajar [18] indicated that these perceptions, in turn, are influenced by factors such as optimism (a
positive view of technology's ability to enhance work efficiency and performance) and innovativeness
(an enthusiasm for trying new technology). Hence, one primary focus of the testing will be to assess
users' willingness and satisfaction with adopting the attendance marking technologies.

1.3 Contributions and Organization

The paper's contributions can be broadly summarized as follows:

i. Developing a web-based student attendance management system that combines facial

recognition technology and QR codes represents an innovative solution, revolutionizing
the way educational institutions track and record student attendance.
ii. Presenting a practical implementation of WSAMS that effectively addresses common
challenges in tracking attendance in real-world educational settings. The system promotes
transparency, facilitates monitoring, and enables the auditing of attendance records to
effectively evaluate academic performance.
iii. Showcasing the potential of adopting face recognition technology using Haar cascade and
LBPH, along with dynamic QR codes, to offer a flexible yet reliable option for automated
attendance marking while reducing the risk of fraudulent attendance reporting.

200
Journal of Advanced Research in Applied Sciences and Engineering Technology
Volume 33, Issue 2 (2024) 198-208

The organization of this paper is as follows: Section 2 discusses the methodologies employed in
developing our system. Section 3 provides a comprehensive explanation of the primary modules in
our proposed system. This includes the face recognition algorithms and stages, as well as the flow of
the QR code attendance marking process. Section 4 presents the results and discussions of the
acceptance testing and evaluation, while Section 5 provides concluding remarks.

2. Methodology

The experimental study was conducted during the first semester of 2022 for selected courses in
the faculty of computing and software engineering (FCSE) at i-CATS University College, where
mandatory attendance was required. The study encompassed three phases: requirement elicitation
and analysis, system design and development, and system testing and evaluation. In Phase 1, the
requirement elicitation and analysis phase commenced with a needs assessment to identify the
requirements and specifications of the attendance system. This entailed conducting interviews with
administrative personnel and lecturers, as well as analysing the existing manual attendance system.
During Phase 2, the focus of system design and development was to meet end-user requirements
by customizing the architecture to their specific needs. An Agile approach was adopted, utilizing
iterative cycles of design, development, and testing. Figure 1 provides a visual representation of the
proposed system's architecture, showcasing key components such as facial recognition technology,
QR code scanning, and a centralized database. In Phase 3, comprehensive testing stages, including
unit testing, integration testing, and acceptance testing, were carried out on the developed system.
Evaluation efforts encompassed assessing module functionalities, gauging user perceptions of
usefulness, and determining their willingness to embrace this innovative solution.

Fig. 1. System architecture

The web system was developed using open-source systems, employing PHP, JavaScript, and
Bootstrap framework for system development and MySQL for database management. Face
recognition was implemented using a Python-based module utilizing the OpenCV library for image
processing, networking with the server, and face image classification. For QR code attendance
recording, a mobile application was designed using Android Studio, incorporating the Volley and
Retrofit APIs for QR scanning functionality. The system development utilized hardware equipment
that included a web server, a monitor, a computer with a webcam, and a smartphone with an internet
connection and camera.

201
Journal of Advanced Research in Applied Sciences and Engineering Technology
Volume 33, Issue 2 (2024) 198-208

3. Web-Based Student Attendance Management System (WSAMS)

WSAMS offers a seamless and efficient process with a user-friendly interface for data entry,
student attendance tracking, addressing absenteeism, and ensuring accurate attendance records.
The web-based system comprises four modules: registration, attendance management, notification,
and attendance marking. The system's development is divided into four stages: Stage 1 involves the
creation of the web-based system, including the registration, attendance management, and
notification modules. Stage 2 focuses on developing the face recognition algorithm, while Stage 3
centres around the QR scanning app. Lastly, Stage 4 encompasses the integration of all modules into
a cohesive system.
The Registration Module facilitates course details setup and student enrolment, captures their
facial data, and associates it with their profiles for attendance tracking. The Attendance Management
Module is responsible for managing attendance records, generating attendance reports, and
visualizing attendance data to identify patterns and anomalies. The Notification Module notifies
lecturers about student absences, facilitates the issuance of absenteeism forms, and automatically
sends emails to counsellors and parents when the absence rates surpass a predetermined threshold.
The Attendance Marking Module provides lecturers with the flexibility to choose their preferred
method for marking attendance, offering two sub-modules: face recognition and QR code.

3.1 Face Recognition

The face recognition system comprises four components: image acquisition, face detection,
feature extraction, classification, and database matching, as depicted in Figure 2. The image
acquisition module captures the image using a camera and feeds it as input to the system. The face
detection module identifies and locates the facial region within the input image. The feature
extraction module examines human identity information and extracts features from the facial region.
The classification module utilizes a trained classifier to match the extracted features with known or
unknown faces. The database matching module compares the extracted feature vector of the input
image to the feature vectors of known faces stored in the database and returns the closest match.

Fig. 2. The process of the face recognition system

Face recognition implementation involved utilizing OpenCV, a renowned open-source computer

vision library known for seamlessly integrating facial recognition algorithms. Haar cascade classifier
and LBPH Face Recognizer were used for face detection and recognition, respectively. Haar classifier
was chosen for its grayscale image capability, enabling efficient detection without relying on colour
information. It demonstrated resilience against grayscale transformations and exhibited exceptional
accuracy and speed. LBPH (Local Binary Patterns Histogram) was selected as the feature extraction
method for effective representation of image texture and structure. It achieved a 90% accuracy rate

202
Journal of Advanced Research in Applied Sciences and Engineering Technology
Volume 33, Issue 2 (2024) 198-208

in recognizing both front-facing and side-facing faces [19,20]. LBPH outperformed Eigenfaces and
Fisherfaces methods in handling lighting and pose variations and showed superior performance
across different variables such as lighting conditions, object distance, and subject age [21].

3.1.1 Face detection and face recognition

The face detection process starts with image capture, loading, and conversion to grayscale. The
Haar cascade classifier is then used to detect faces, categorizing images as positive (with a face) or
negative (without a face) [22]. This classification relies on a trained classifier that determines if a new
image is positive or negative based on a dataset of face and non-face images. If a face is detected,
the system analyses facial features and verifies the presence of both eyes. Once successful eye
detection occurs, the face image is normalized in size and orientation, and a rectangular frame is
drawn around the detected face.
The LBPH method represents and reduces the dimensionality of face images. It divides the image
into non-overlapping blocks, applies histogram equalization for contrast enhancement, and assigns
binary values based on pixel comparisons with its surrounding 3x3 pixels. These binary values
contribute to the creation of LBP histograms, which are concatenated to generate a feature
histogram capturing distinctive image features for accurate recognition. The LBPH face recognition
process involves multiple steps: feature extraction, comparison to a database of known face
histograms, computation of similarity using a distance metric, and determination of the closest
match. Figure 3 shows a captured image and the corresponding recognized student.

Fig. 3. The Example of Captured Image and Recognized Student

3.2 QR Code Scanning

The flow process for students to mark their attendance by scanning QR codes is depicted in Figure
4. The process starts with the lecturer accessing the web-based system and selecting the appropriate
class session.

203
Journal of Advanced Research in Applied Sciences and Engineering Technology
Volume 33, Issue 2 (2024) 198-208

Fig. 4. Flow process for QR code scanning attendance

Subsequently, a dynamic QR code is generated, as depicted in Figure 5, which updates every 15

seconds to prevent fraudulent attendance through code sharing. A mobile app has been developed
for students to log in and scan the QR code for attendance marking.

Fig. 5. Class attendance QR code generator

Figure 6 displays the interfaces of the Student Attendance App designed for QR code scanning.
Once successfully logged in to confirm their identity, the application verifies their enrolment status
in the class and records their attendance, which is then updated in the database. To avoid multiple
scans, the system is designed to disregard any subsequent scans of the same code by the same
student.

204
Journal of Advanced Research in Applied Sciences and Engineering Technology
Volume 33, Issue 2 (2024) 198-208

(a) (b) (c) (d)

Fig. 6. Attendance app screens (a) Login screen (b) Scanner launcher home screen (c)
Successful student attendance taking (d) Unsuccessful student attendance taking

4. Result and Discussion

To ensure voluntary adoption of an attendance system, it is crucial to ensure that its features and
technology are applicable to the intended users. In order to evaluate the effectiveness of our
proposed system, we conducted two system tests for five courses at FCSE, involving 30 students. The
initial trial involved a paper-based attendance recording, known as the manual system, while the
subsequent experiment utilized face recognition and QR code scanning separately for attendance
marking, referred to as the automated system. We recorded the time taken by each student to log
their attendance during lecture periods for both experiments, and the results are presented in Figure
7.

Fig. 7. Attendance Marking Time per Student on Average

Additionally, we selected five lecturers to perform an alpha test on the attendance management
system. The participating lecturers were granted system access and assigned various attendance-
related tasks, including marking attendance, viewing attendance records, and generating reports.
Table 1 presents a comparison of the time analysis for attendance tracking between the automated
and manual systems. The results indicate a substantial time advantage of the automated system over
the manual system in overall attendance tracking. Specifically, the automated system achieved a total
time savings of 28.25 minutes for the 30 students involved in attendance marking.

205
Journal of Advanced Research in Applied Sciences and Engineering Technology
Volume 33, Issue 2 (2024) 198-208

Table 1
Time analysis for attendance tracking: automated system (face recognition) vs manual system
Process Automated System Manual System Time Saved
Marking attendance 2 seconds per 12.5 seconds per 10.5 seconds per
student student student
Recording Attendance 1 minute 10 minutes 9 minutes
Generating Attendance Sheet 1 minute 15 minutes 14 minutes
Total Time Spent for 30 Students 3 minutes 31.25 minutes 28.25 minutes
(approximately)

Table 2 presents the average user ratings for system usability, showcasing highly satisfactory
results. The data reveals that the system has achieved a remarkable overall user satisfaction score of
4.7 out of 5.

Table 2
Average user ratings for system usability
Criteria Ease of User Responsiveness Visual Error Overall Average User
Use Friendliness Design Handling Satisfaction Rating
Average 4.6 4.5 4.7 4.8 4.9 4.7 4.7
Rating

Table 3 displays the testing results and feedback for improving modules in WSAMS. Participating
lecturers confirmed the system's suitability for efficiently managing student attendance, providing a
quick and hassle-free method for attendance marking and record viewing. Administrative personnel
have reported that the system effectively facilitates auditing tasks, ensuring strict compliance with
institutional standards. Feedback showed 85% of students preferred face recognition for its
convenience, speed, contactless nature, and real-time identification capability. In contrast, 15% of
students opted for QR scanning to avoid queues and address privacy concerns. Remarkably, neither
method was rejected by any students. There is considerable optimism about its potential to improve
work efficiency, enhance performance, and embrace innovative technologies.

Table 3
Testing Results and User Feedback for Improving WSAMS Modules
No Module Results Feedback for Improvement
1 Registration Efficiently managing course registration and administration To provide an import feature
for specific sessions, lecturers, and enrolled students, the for registered data, along
system effectively captures detailed information and with summary statistics.
simplifies face setup through clear instructions.
2 Attendance Accurately records and updates attendance, provides easy Enhance formatting options
Management accessibility to records, generates accurate reports with and user interface design.
seamless data export, and includes summarized statistics.
3 Notification Successfully identifies absenteeism threshold violations, Incorporating notification
generates attendance warning forms, and promptly logs and exploring SMS or
triggers the notification process. mobile app notifications.
4 Face Achieves an average processing time of 1-3 seconds per Consider leveraging multi-
recognition student when they are positioned in front of the camera face recognition.
and the system is appropriately calibrated.
5 QR scanning On average, students took approximately 5.5 seconds to Suggest exploring the
scan and perform a bulk upload, assuming a successful possibility of offline support
login and a stable internet connection. for QR scanning.

206
Journal of Advanced Research in Applied Sciences and Engineering Technology
Volume 33, Issue 2 (2024) 198-208

5. Conclusion

In general, the use of a centralized web-based student attendance management system offers
several benefits, including easy access to attendance records, streamlined record-keeping, improved
tracking accuracy and efficiency, reduced faculty and administrative workload, and the creation of
an engaging learning environment. The attendance management system, including post-processing,
received positive feedback during testing. Based on our findings, face recognition emerges as the
preferred method for attendance marking, although QR scanning is favoured by some. Offering
multiple attendance marking options enhances user satisfaction, providing both a quicker and more
reliable method while ensuring a seamless experience without extra devices. We envision further
research to expedite attendance marking by enabling multi-face recognition and offline support for
QR code scanning in low-internet scenarios. In summary, these findings can serve as a foundation for
any future considerations aimed at optimizing attendance management in an increasingly
technology-driven educational landscape.

Acknowledgement
This research received financial support from i-CATS University College.

References
[1] Westerman, James W., Luis A. Perez‐Batres, Betty S. Coffey, and Richard W. Pouder. "The relationship between
undergraduate attendance and performance revisited: Alignment of student and instructor goals." Decision
Sciences Journal of Innovative Education 9, no. 1 (2011): 49-67. https://doi.org/10.1111/j.1540-4609.2010.00294.x
[2] Dobkin, Carlos, Ricard Gil, and Justin Marion. "Skipping class in college and exam performance: Evidence from a
regression discontinuity classroom experiment." Economics of Education Review 29, no. 4 (2010): 566-575.
https://doi.org/10.1016/j.econedurev.2009.09.004
[3] Jaafar, Nurulaini, Siti Rohani Mohd Nor, Siti Mariam Norrulashikin, Nur Arina Bazilah Kamisan, and Ahmad Qushairi
Mohamad. "Increase Students’ Understanding of Mathematics Learning Using the Technology-Based
Learning." International Journal of Advanced Research in Future Ready Learning and Education 28, no. 1 (2022): 24-
29.
[4] Fuzail, Muhammad, Hafiz Muhammad Fahad Nouman, Muhammad Omer Mushtaq, Binish Raza, Awais Tayyab, and
Muhammad Waqas Talib. "Face detection system for attendance of class’ students." International journal of
multidisciplinary sciences and engineering 5, no. 4 (2014).
[5] Raghuwanshi, Anshun, and Preeti D. Swami. "An automated classroom attendance system using video based face
recognition." In 2017 2nd IEEE International Conference on Recent Trends in Electronics, Information &
Communication Technology (RTEICT), pp. 719-724. IEEE, 2017. https://doi.org/10.1109/RTEICT.2017.8256691
[6] Chintalapati, Shireesha, and M. V. Raghunadh. "Automated attendance management system based on face
recognition algorithms." In 2013 IEEE International conference on computational intelligence and computing
research, pp. 1-5. IEEE, 2013. https://doi.org/10.1109/ICCIC.2013.6724266
[7] Chinimilli, Bharath Tej, T. Anjali, Akhil Kotturi, Vihas Reddy Kaipu, and Jathin Varma Mandapati. "Face recognition
based attendance system using Haar cascade and local binary pattern histogram algorithm." In 2020 4th
international conference on trends in electronics and informatics (ICOEI)(48184), pp. 701-704. IEEE, 2020.
[8] Soon, Tan Jin. "QR code." synthesis journal 2008 (2008): 59-78.
[9] Shin, Dong-Hee, Jaemin Jung, and Byeng-Hee Chang. "The psychology behind QR codes: User experience
perspective." Computers in Human Behavior 28, no. 4 (2012): 1417-1426.
https://doi.org/10.1016/j.chb.2012.03.004
[10] Ohbuchi, Eisaku, Hiroshi Hanaizumi, and Lim Ah Hock. "Barcode readers using the camera device in mobile phones."
In 2004 International Conference on Cyberworlds, pp. 260-265. IEEE, 2004.
[11] Nuhi, Asri, Agon Memeti, Florinda Imeri, and Betim Cico. "Smart attendance system using qr code." In 2020 9th
Mediterranean Conference on Embedded Computing (MECO), pp. 1-4. IEEE, 2020.
https://doi.org/10.1109/MECO49872.2020.9134225
[12] Wei, Xiong, Anupam Manori, Nandgopal Devnath, Nitin Pasi, and Vivek Kumar. "QR Code Based Smart Attendance
System." International Journal of Smart Business and Technology 5, no. 1 (2017): 1-10.
https://doi.org/10.21742/ijsbt.2017.5.1.01

207
Journal of Advanced Research in Applied Sciences and Engineering Technology
Volume 33, Issue 2 (2024) 198-208

[13] Masalha, Fadi, and Nael Hirzallah. "A students attendance system using QR code." International Journal of
Advanced Computer Science and Applications 5, no. 3 (2014). https://doi.org/10.14569/IJACSA.2014.050310
[14] Nalintipwong, Srinual, Thanarat Tasarika, Chayut Ruksomya, Sirion Vittayakorn, and Thanisa Numnonda.
"Concurrent self-identification applying qr code to record class attendance (qrclass)." In 2019 IEEE 9th International
Conference on Electronics Information and Emergency Communication (ICEIEC), pp. 1-5. IEEE, 2019.
https://doi.org/10.1109/ICEIEC.2019.8784518
[15] Mijić, Danijel, Ognjen Bjelica, Jelena Durutović, and Miloš Ljubojević. "An improved version of student attendance
management system based on RFID." In 2019 18th International Symposium INFOTEH-JAHORINA (INFOTEH), pp. 1-
5. IEEE, 2019. https://doi.org/10.1109/INFOTEH.2019.8717750
[16] Masrom, Maslin, Mohd Nazry Ali, Wahyunah Ghani, and Amirul Haiman Abdul Rahman. "The ICT implementation
in the TVET teaching and learning environment during the COVID-19 pandemic." International Journal of Advanced
Research in Future Ready Learning and Education 28, no. 1 (2022): 43-49.
[17] Davis, Fred D. "Perceived usefulness, perceived ease of use, and user acceptance of information technology." MIS
quarterly (1989): 319-340. https://doi.org/10.2307/249008
[18] Nugroho, Mahendra Adhi, and M. Andryzal Fajar. "Effects of technology readiness towards acceptance of
mandatory web-based attendance system." Procedia Computer Science 124 (2017): 319-328.
https://doi.org/10.1016/j.procs.2017.12.161
[19] Ahmed, Aftab, Jiandong Guo, Fayaz Ali, Farha Deeba, and Awais Ahmed. "LBPH based improved face recognition at
low resolution." In 2018 international conference on Artificial Intelligence and big data (ICAIBD), pp. 144-147. IEEE,
2018. https://doi.org/10.1109/ICAIBD.2018.8396183
[20] Singh, Aruni, Sanjay Kumar Singh, and Shrikant Tiwari. "Comparison of face recognition algorithms on dummy
faces." The International Journal of Multimedia & Its Applications 4, no. 4 (2012): 121.
https://doi.org/10.5121/ijma.2012.4411
[21] Özdil, Ahmet, and Metin Mete Özbilen. "A survey on comparison of face recognition algorithms." In 2014 IEEE 8th
International Conference on Application of Information and Communication Technologies (AICT), pp. 1-3. IEEE,
2014. https://doi.org/10.1109/ICAICT.2014.7035956
[22] Rasras, Rashad J., Bilal Zahran, Mutaz Rasmi Abu Sara, and Ziad AlQadi. "Developing digital signal clustering method
using local binary pattern histogram." International Journal of Electrical and Computer Engineering (IJECE) 11, no.
1 (2021): 872-878. https://doi.org/10.11591/ijece.v11i1.pp872-878

208