Enhancing Face Authentication for Online Examination Systems Using Median Filtering and MobileNetV2

Dadang Sudrajat; Dian Ade Kurnia; Rudi Kurniawan; Othman bin Mohd; Maulana Sujarwadi; Salman Alfarizi

doi:10.29207/resti.v9i6.7185

Authors

Dadang Sudrajat STMIK IKMI Cirebon
Dian Ade Kurnia STMIK IKMI Cirebon
Rudi Kurniawan STMIK IKMI Cirebon
Othman bin Mohd Universiti Teknikal Malaysia Melaka
Maulana Sujarwadi STMIK IKMI Cirebon
Salman Alfarizi STMIK IKMI Cirebon

DOI:

https://doi.org/10.29207/resti.v9i6.7185

Keywords:

digital transformation, face authentication, median filtering, MobilNetV2, online assesment

Abstract

Digital transformation in higher education is driving the uptake of online tests, which require academic integrity, security, and robust user experience. In the context of authentication of users, deep learning based face recognition, in particular the Convolutional Neural Network (CNN) architectures, such as MobileNetV2, combined with intermediate filter, promises to deliver a consistent performance across a wide range of devices and imaging environments. However, there are limited comprehensive studies evaluating the final integration of the median filter and MobileNetV2 in high-value test scenarios. This study contributes by proposing an effective end-to-end Face Authentication Pipeline, assessing the median impact of filtering on MobileNetV2 performance, and validating it with a prototype application. The authentic face dataset was collected using the Teachable Machine, preprocessed with cropping, resizing, and median filtering, and then augmented through rotation, shift, shear, zoom, reversal, and brightness adjustment. The MobileNetV2 model was trained with Adam in a stepwise manner, starting with 0.001 and then 0.0001 for 20 epochs in a batch size of 32, and was evaluated for accuracy, precision, recall, and F1 score. Results show that the accuracy curve has remained stable at almost 95 percent during the 20th epoch; most grades achieved 1.00 in both precis, recall and F1, with some classings showing a limited decrease due to facial similarity or expression differences. These findings confirm that MobileNetV2 median filtering can be the basis for an effective, accurate and ready to integrate face recognition in online testing applications on a wide range of devices.

Downloads

Download data is not yet available.

References

M. Hammad, Y. Liu, and K. Wang, “Multimodal Biometric Authentication Systems Using Convolution Neural Network Based on Different Level Fusion of ECG and Fingerprint,” Ieee Access, vol. 7, pp. 26527–26542, 2019, doi: 10.1109/access.2018.2886573.

A. F. Teixeira and M. Jos, “How Higher Education Institutions Are Driving to Digital Transformation: A Case Study,” Educ. Sci., vol. 11, no. 10, pp. 1–14, 2021, [Online]. Available: https://www.mdpi.com/2227-7102/11/10/636

D. Saha, S. Das, and D. Acharjee, “Exploring the Efficacy and Implementation of an Online Examination System : A Comprehensive Study on eXamPro in Modern Education,” no. December, 2023.

S. H. Himel, M. A. Iqbal, M. I. Rana, and T. Mozumder, “Face-App: A Real-Time Face Recognition E-Attendance System for Digital Learning,” Glob. J. Eng. Technol. Adv., vol. 11, no. 1, pp. 13–24, 2022, doi: 10.30574/gjeta.2022.11.1.0049.

M. Rukhiran, S. Wong-In, and P. Netinant, “IoT-Based Biometric Recognition Systems in Education for Identity Verification Services: Quality Assessment Approach,” Ieee Access, vol. 11, pp. 22767–22787, 2023, doi: 10.1109/access.2023.3253024.

S. Coghlan, T. Miller, and J. M. Paterson, “Good Proctor or ‘Big Brother’? Ethics of Online Exam Supervision Technologies,” Philos. Technol., vol. 34, no. 4, pp. 1581–1606, 2021, doi: 10.1007/s13347-021-00476-1.

I. Adjabi, A. Ouahabi, A. Benzaoui, and A. Taleb-Ahmed, “Past, present, and future of face recognition: A review,” Electron., vol. 9, no. 8, pp. 1–53, 2020, doi: 10.3390/electronics9081188.

S. Xu, K. I. Khan, and M. F. Shahzad, “Examining the Influence of Technological Self-Efficacy, Perceived Trust, Security, and Electronic Word of Mouth on ICT Usage in the Education Sector,” Sci. Rep., vol. 14, no. 1, 2024, doi: 10.1038/s41598-024-66689-4.

S. Raje and S. E. Stitzel, “Strategies for Effective Assessments While Ensuring Academic Integrity in General Chemistry Courses During COVID-19,” J. Chem. Educ., vol. 97, no. 9, pp. 3436–3440, 2020, doi: 10.1021/acs.jchemed.0c00797.

A. B. S. Salamh and H. İ. Akyüz, “New Deep Learning Model for Face Recognition and Registration in Distance Learning,” Int. J. Emerg. Technol. Learn., vol. 17, no. 12, pp. 29–41, 2022, doi: 10.3991/ijet.v17i12.30377.

F. Kharbat and A. A. Daabes, “E-Proctored Exams During the COVID-19 Pandemic: A Close Understanding,” Educ. Inf. Technol., vol. 26, no. 6, pp. 6589–6605, 2021, doi: 10.1007/s10639-021-10458-7.

N. E. L. Fadel, “Facial Recognition Algorithms : A Systematic Literature Review,” 2025.

A. Ullah, H. Xiao, and T. Barker, “A Dynamic Profile Questions Approach to Mitigate Impersonation in Online Examinations,” J. Grid Comput., vol. 17, no. 2, pp. 209–223, 2018, doi: 10.1007/s10723-018-9442-6.

M. Garlinska, M. Osial, and K. Proniewska, “The Influence of Emerging Technologies on Distance Education,” 2023.

S. Liu, Y. Song, M. Zhang, J. Zhao, S. Yang, and K. Hou, “An Identity Authentication Method Combining Liveness Detection and Face Recognition,” Sensors, vol. 19, no. 21, p. 4733, 2019, doi: 10.3390/s19214733.

R. Mishra, N. Mittal, and S. K. Khatri, “Digital Image Restoration using Image Filtering Techniques,” 2019 Int. Conf. Autom. Comput. Technol. Manag. ICACTM 2019, pp. 268–272, 2019, doi: 10.1109/ICACTM.2019.8776813.

D. Mishra, N. Roy, M. Bapat, and A. Gudipalli, “Performance Evaluation of Brain Tumor Detection Using Watershed Segmentation and Thresholding,” Int. J. Smart Sens. Intell. Syst., vol. 14, no. 1, pp. 1–12, 2021, doi: 10.21307/ijssis-2021-020.

B. r. c. Joseph, I. J. Jebadurai, G. J. L. Paulraj, J. Jebadurai, and M. M. VARUVEL, “Deep Vein Net: Deep Vein Thrombosis Identification via Sooty Tern Optimized Deep Learning Network,” RRST-Ee, vol. 69, no. 1, pp. 115–120, 2024, doi: 10.59277/rrst-ee.2024.1.20.

Y. Huang, W. Dai, and S. He, “Strategies for Marine Remote Sensing Target Detection Based on Deep Learning Model and Internal Wave Simulation Imaging Technology,” Appl. Math. Nonlinear Sci., vol. 9, no. 1, 2023, doi: 10.2478/amns.2023.1.00125.

S. Dou, L. Wang, D. Fan, L. Miao, J. Yan, and H. He, “Classification of Citrus Huanglongbing Degree Based on CBAM-MobileNetV2 and Transfer Learning,” Sensors, vol. 23, no. 12, pp. 1–18, 2023, doi: 10.3390/s23125587.

B. Liu, D. Zou, L. Feng, S. Feng, P. Fu, and J. Li, “An FPGA-based CNN accelerator integrating depthwise separable convolution,” Electron., vol. 8, no. 3, 2019, doi: 10.3390/electronics8030281.

M. Ye and J. Zhang, “Mobip: a lightweight model for driving perception using MobileNet,” Front. Neurorobot., vol. 17, 2023, doi: 10.3389/fnbot.2023.1291875.

K. Guo et al., “Efficient Adaptive Incremental Learning for Fruit and Vegetable Classification,” Agronomy, vol. 14, no. 6, 2024, doi: 10.3390/agronomy14061275.

D. A. Kurnia, S. Risnanto, Sugiyatno, A. N. Kusuma, Y. Naufal, and O. Bin Mohd, “Enhance Low-Resolution Face Recognition Accuracy Using Median and Mean Filtering Techniques Based on Convolutional Neural Networks (CNN),” in 2024 18th International Conference on Telecommunication Systems, Services, and Applications (TSSA), IEEE, Oct. 2024, pp. 1–7. doi: 10.1109/TSSA63730.2024.10864112.

G. M. Kosgiker, A. Deshpande, and K. Anjum, “An Efficient Network‐based Skin Lesion Segmentation in Dermoscopic Images,” Int. J. Imaging Syst. Technol., vol. 31, no. 2, pp. 874–894, 2021, doi: 10.1002/ima.22545.

A. Ghanad, “An Overview of Quantitative Research Methods,” Int. J. Multidiscip. Res. Anal., vol. 06, no. 08, pp. 3794–3803, 2023, doi: 10.47191/ijmra/v6-i8-52.

J. Siswantoro, J. Rahmadiarto, and M. F. Naufal, “Facial Expression Recognition to Detect Student Engagement in Online Lectures,” Teknika, vol. 13, no. 2, pp. 226–232, 2024, doi: 10.34148/teknika.v13i2.853.

M. H. Lee and S. Y. Shin, “Modified Pixels Based Fast Median Filter in Impulse Noise Environments,” Indones. J. Electr. Eng. Comput. Sci., vol. 9, no. 3, p. 731, 2018, doi: 10.11591/ijeecs.v9.i3.pp731-741.

Q. H. Nguyen et al., “Influence of data splitting on performance of machine learning models in prediction of shear strength of soil,” Math. Probl. Eng., vol. 2021, 2021, doi: 10.1155/2021/4832864.

E. Lopez, J. Etxebarria-Elezgarai, J. M. Amigo, and A. Seifert, “The importance of choosing a proper validation strategy in predictive models. A tutorial with real examples,” Anal. Chim. Acta, vol. 1275, no. February, p. 341532, 2023, doi: 10.1016/j.aca.2023.341532.

A. Mumuni and F. Mumuni, “Data augmentation: A comprehensive survey of modern approaches,” Array, vol. 16, no. August, p. 100258, 2022, doi: 10.1016/j.array.2022.100258.

M. J. Adamu et al., “Efficient and Accurate Brain Tumor Classification Using Hybrid MobileNetV2–Support Vector Machine for Magnetic Resonance Imaging Diagnostics in Neoplasms,” Brain Sci., vol. 14, no. 12, 2024, doi: 10.3390/brainsci14121178.

S. Ahmad, “An Efficient Optimization Technique for Training Deep Neural Networks,” 2023.

J. H. Cabot and E. G. Ross, “Evaluating prediction model performance,” Surgery, vol. 174, no. 3, pp. 723–726, 2023, doi: 10.1016/j.surg.2023.05.023.

A. Rayeni and H. Naderi, “Predicting the Canadian Yield Curve Using Machine Learning Techniques,” pp. 1–30, 2025.

E. E. B. Adam and S. Sathesh, “Evaluation of Fingerprint Liveness Detection by Machine Learning Approach - A Systematic View,” J. Ismac, vol. 3, no. 1, pp. 16–30, 2021, doi: 10.36548/jismac.2021.1.002.

Z. Akhtar and G. L. Foresti, “Face Spoof Attack Recognition Using Discriminative Image Patches,” J. Electr. Comput. Eng., vol. 2016, pp. 1–14, 2016, doi: 10.1155/2016/4721849.

A. M. Elkhatat, “Practical Randomly Selected Question Exam Design to Address Replicated and Sequential Questions in Online Examinations,” Int. J. Educ. Integr., vol. 18, no. 1, 2022, doi: 10.1007/s40979-022-00103-2.