REFERENCES:
Devi, M. V., Surya, K. J., Meethashree, E., Keerthivasan, V. S., & Saraswathy, S. (2024, April). Nonlinear
SVM Classifier based Online Attendance System for Facial Recognition and Mask Detection. In 2024
International Conference on Knowledge Engineering and Communication Systems (ICKECS) (Vol. 1, pp. 1-
6). IEEE.
Eridani, D., Widianto, E. D., Windasari, I. P., Bawono, W. B., & Gunarto, N. F. (2021). Internet of things
based attendance system design and development in a smart classroom. Indonesian Journal of Electrical
Engineering and Computer Science, 23(3), 1432-1439.
Gaur, S., Pandey, M., & Himanshu. (2024). Realization of Facial Recognition Technology for Attendance
Monitoring Through Biometric Modalities Employing MTCNN Integration. SN Computer Science, 5(7),
862.
Bharathi, B. (2021, June). Cloud Based Attendance Application Using Face Recognition. In 2021 5th
International Conference on Trends in Electronics and Informatics (ICOEI) (pp. 881-890). IEEE.
Nidhya, R., Pabi, D. A., DivyaSree, U., Abhishek, B., Harika, A., & Alim, S. A. (2024, April). Exploring Facial
Recognition Technologies for Classroom Management. In 2024 10th International Conference on
Communication and Signal Processing (ICCSP) (pp. 1702-1707). IEEE.
The main objective of this project is to provide a streamlined attendance management system that can
be accessed through web browsers, removing the requirement for the installation of specialised
software. The technology utilises facial biometrics to identify users, storing profiles with facial picture
samples in a centralised online database. Before implementing facial recognition, the system goes
through a model training phase where Support Vector Machines (SVM) are used to create a strong
recognition model. Moreover, synthetic data is utilised to train the algorithm in recognising individuals
who are wearing facial masks. The server-side application is developed using Python and utilises the
OpenCV library for image processing.
This research proposes an attendance system in the smart classroom which supports the system’s
previous activities as well as its integration with security and classroom management. In this system, the
NodeMCU which was connected to the Wi-Fi router served as the controller, while the fingerspot revo
FF-153BNC functioned as the system input. In addition, the database server was used to allocate
attendee and classroom management data. This system is connected with the information system and
classroom display unit, and component and system testing were applied in this research. The results
showed that each system unit successfully integrated and managed the attendance, security, and
classroom schedule.
This paper proposes a novel method that merges facial recognition using K-nearest neighbours (KNN)
and multi-task cascaded convolutional networks (MTCNN) via a Flask-based web application. The
system's goal is to increase accuracy, especially in situations where masks partially conceal faces.
Importing the required libraries and configuring a Flask application are part of the implementation. To
improve context, pictures containing dates are taken when a user registers. MTCNN is used to address
localization issues and increase the accuracy of face detection. The system makes sure that directories
are managed correctly, which includes making folders for daily attendance records. Tracking user
registration, extracting facial features with HaarCascade, identifying faces using a trained KNN model,
and training the KNN model with readily available facial data are some of the main features. MTCNN
demonstrates a considerable improvement by significantly increasing recognition accuracy. This
combined system exemplifies the collaboration capabilities of Flask, MTCNN, HaarCascade, and KNN
models by showcasing the real-world implementation of sophisticated convolutional networks in an
intuitive interface. Experimental findings validate the system's efficacy in well-lit, unobstructed
surroundings, with a recognition accuracy of 92.59–97.36% under ideal conditions.
*******************************_______________**************
The goal of this research is to create a sophisticated system for gathering student data that is suitable
for use in classroom settings. The approach begins with taking pictures of every student in the class in a
methodical manner. Next, advanced image processing techniques like segmentation are used to extract
unique traits, which are subsequently converted into structured pixel values in an array. These extracted
characteristics are used to train a model by utilizing machine learning capabilities, including the use of
OpenCV, a powerful computer vision toolkit, and facial recognition algorithms. The system is able to
anticipate student presence with 99.38% accuracy. Instantaneous insights into students entering the
classroom are made possible by real-time person detection implemented with OpenCV. Carefully logging
these entries, which include important date and time information, results in a daily compilation that is
saved as a text file and forms an extensive database. This database provides insightful information on
attendance trends over time in addition to streamlining the recording of attendance.
