Innovation the smart-integrated classroom: Combining user authentication and emotion assessment
DOI:
https://doi.org/10.61591/jslhu.18.506Keywords:
MTCNN, Facenet, Deep learning, User Authentication, Emotion recognition, Convolutional Neural NetworksAbstract
The innovation of the smart integrated classroom solution in the research utilizes MTCNN and FaceNet techniques to develop a system capable of verifying user information based on facial recognition. Moreover, the application can perform features such as attendance verification, detecting users in a group of multiple people, and assessing the emotions of learners. We have compared the user verification model with several models such as MTCNN and FaceNet, VGG16, and OpenVino. The results show that the combination of MTCNN and FaceNet achieved optimal accuracy, up to 96.4%, for the task of user identification to serve the attendance function for learners. Additionally, for the emotion assessment function, the study uses convolutional neural networks (CNN) based on the Fer2013 and Fer Plus datasets to evaluate the emotional states of learners during exams. The innovation of the smart integrated classroom management system, based on facial recognition using MTCNN and FaceNet, along with the emotional assessment feature for learners in universities, can enhance teaching effectiveness, improve training quality, and monitor the status of students during exams.
References
Kaipeng zhang và cộng sự, Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks, 2016.
XianBen Yang và Wei Zhang, Heterogeneous face detection based on multi-task cascaded convolutional neural network, IET Image Processing, 2021.
Pilli Bhavya Sri cùng đồng tác giả, Harnessing Security Improvements Using FaceNet Approach for Face Recognition System, IEEE, 2024.
Siyu Jia, Ying Tian, Face detection based on improved multi-task cascaded convolutional neural networks, IAENG international journal of computer science, 2024.
Ian j. goodfellow và Đồng tác giả, "Challenges in Representation Learning: A report on three machine learning contests", 2013.
Brijesh Bakariya và đồng sự, Facial emotion recognition and music recommendation system using CNN-based deep learning techniques, Evolving Systems 15, Volume 15, pages 641–658, 2024.
Emad barsoum và đồng tác giả, "Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distribution", 2016.
Abbas Khalifa Nawar, Hadi Raheem Ali, Mothefer Majeed Jahefer, Sabah Abdulazeez Jebur, "Automate facial paralysis detection using vgg architectures", ijciar.v7i1.158, Volume 7, Issue 1, 2024.
Alexander demidovskij và đồng tác giả, "openvino Deep Learning Workbench: Towards Analytical Platform for Neural Networks Inference Optimization", Journal of Physics: Conference Series, 2021.
Jiawei Huang và Ding Zhou, A scalable real-time computer vision system for student posture detection in smart classrooms, SpringerLink, Volume 29, pages 917–937, 2024.
Siyao Qi và đồng tác giả, "Face Recognition Model Based On MTCNN And Facenet”, IEEE, 2022.
R E Saragih, Q H To, A Survey of Face Recognition Based on Convolutional Neural Network, ndonesian Journal of Information Systems (IJIS) Vol. 4, No. 2, February 2022.
Rahmeh Abou Zafra, Lana Ahmad Abdullah, Rouaa Alaraj, Rasha Albezreh, Tarek Barhoum, Khloud Al Jallad, An experimental study in Real-time Facial Emotion Recognition on new 3RL dataset, Computer Vision and Pattern Recognition, 2023.
Tony Gwyn, Kaushik Roy, Mustafa Atay, "Face Recognition Using Popular Deep Net Architectures: A Brief Comparative Study", 2021.
