Leveraging Generative AI and Microlearning to Enhance Facial Recognition for Flexible Higher Education in Africa
Keywords:
Generative AI, Microlearning, Facial Recognition, Open and Distance Learning, Higher Education in AfricaAbstract
Facial recognition technology has significantly impacted various fields, including security, surveillance, and personalised learning. However, challenges related to accuracy, bias, and data privacy remain critical concerns, particularly in higher education contexts where identity verification and remote learning solutions are essential. This study explores how Generative AI (GenAI) and microlearning can enhance facial recognition systems, fostering improved efficiency, accuracy, and ethical deployment in open, distance, and flexible learning (ODFL) environments across Africa. Microlearning - an instructional approach that delivers content in small, manageable units - can optimise algorithmic performance by refining model training and improving recognition accuracy. The research employs a pragmatism paradigm, integrating a quantitative methodology with an experimental approach to assess the impact of GenAI on facial recognition models utilising eigenfaces and dimensionality reduction techniques. The k-means clustering method is applied to analyse object attributes, evaluating the trade-offs between information loss and computational efficiency. Findings suggest that while reducing dimensionality enhances processing speed, it may impair differentiation between individuals, necessitating a balance between feature extraction and dataset expansion. GenAI demonstrated potential in refining feature representations, yet concerns regarding reliability, costs, and ethical considerations persist. The study underscores the importance of a multi-faceted AI integration strategy, addressing data privacy, cybersecurity, and regulatory compliance within the African higher education sector. Future research should explore adaptive AI-driven solutions that enhance learner authentication and engagement in ODFL settings, ensuring inclusive and secure digital learning environments.
References
Agzamova, D. (2023). Enhancing face recognition with contrastive convolutional networks. Journal of AI Research, 34(2), 89-102.
Agzamova, L. (2023). Enhancing facial recognition systems through contrastive CNNs. Journal of Advanced Neural Systems, 18(3), 219–234.
Agzamova, M. (2023). Novel approaches like contrastive CNNs have shown promise in improving recognition accuracy under varying conditions. Journal of Machine Learning Research, 54(2), 102-118.
Almeida, A., Ballard, A., & Wright, C. (2021). Ethical implications of facial recognition technology: Biases, accountability, and privacy concerns. Journal of Information Ethics, 30(1), 45-62.
B. S., R., & J., M. (2023). Key preprocessing techniques for facial recognition. International Journal of Computer Vision Research, 27(4), 58–72.
B. S., T., et al. (2023). Feature extraction using CNNs for facial recognition in varying conditions. International Journal of Machine Learning, 25(4), 152-168.
Blank, G. (2019). AI4People's ethics guidelines for trustworthy AI. Journal of Ethical and Legal Issues in AI, 12(4), 77-102.
Boutros, F., Damer, N., & Kirchbuchner, F. (2023). Synthetic data generation for privacy-friendly face recognition systems. Journal of Privacy and Data Security, 18(2), 120-134.
Casula, M. (2021). Exploratory research methodologies and applications. Methods and Practices in Qualitative Studies, 19(2), 109–127.
Casula, M. (2021). Exploring novel topics through exploratory research design. Research Methodology Quarterly, 15(1), 22-35.
Chen, J. (2023). Personalised learning and the development of 21st-century competencies through generative AI. Journal of Educational Technology Research and Development, 41(3), 450-465.
Chen, L., et al. (2021). Comparing A3C and Q-Learning for reinforcement learning tasks. Machine Learning Journal, 19(3), 212-227.
Chen, Z. (2023). Ethical considerations in AI-based facial recognition: Implications for education. Journal of AI Ethics, 14(1), 45-58.
Dergaa, A., Okaibedi, C., & Zhang, Q. (2023). Generative AI in higher education: Opportunities and challenges for academic integrity. International Journal of Educational Technology, 19(2), 112-128.
Dileep, P. K. (2022). Abductive approach in exploratory research: A method for alternating between induction and deduction. Research Methods in Social Sciences, 47(2), 130-145.
Falade, O. (2023). Generative AI in cybersecurity: Threats and opportunities. Cybersecurity Review, 9(3), 15-22.
Falade, O. (2023). Social engineering attacks amplified by generative AI: An exploration of phishing and deepfakes. Cybersecurity Insights, 10(3), 56-70.
Foley, D., & Sammon, J. W. (2015). Dimensionality reduction through feature extraction: Foundations and applications. Journal of Artificial Intelligence Research, 22(3), 33-50.
George, J., Ravi, V., & Prasad, M. (2020). Face recognition using generative adversarial networks: A survey. International Journal of Computer Vision, 128(4), 768-792.
Jain, A., Lee, K., & Kim, H. (2023). Mitigating racial bias in facial recognition systems using synthetic datasets from biased StyleGAN2 models. International Journal of Artificial Intelligence Research, 47(2), 134–153.
Kabanda, G. (2022). Face Recognition in Machine Learning: A Framework for Dimensionality Reduction Algorithms. International Journal of Advanced Networking and Applications, 14(2), 5396-5407.
Kabanda, G. (2023). Reinforcement learning: A3C algorithm and its efficiency over DQNs. Machine Learning Applications in Cybersecurity, 7(1), 88-102.
Kabanda, G., Chipfumbu, C. & Chingoriwo, T. (2023). A Reinforcement Learning paradigm for Cybersecurity Education and Training. The Oriental Journal of Computer Science and Technology, 16(1).
Kenthapadi, K., Bhaskar, V., & Kumar, A. (2023). Mitigating demographic biases in AI systems. Artificial Intelligence Ethics, 8(1), 37-55.
Kenthapadi, K., Raut, S., & Kumar, R. (2023). Ethical implications and governance of generative AI technologies. Journal of Technology and Society, 17(2), 94-112.
Khosravy, M., & Amirgaliyev, B. (2022). Privacy concerns in AI-powered model inversion attacks: The future of secured recognition systems. Journal of Cybersecurity and Data Protection, 13(4), 245-263.
Khosravy, M., Kamrani, A., & Prakash, A. (2022). Model inversion attacks in AI systems: A survey and case study in facial recognition. Journal of Cybersecurity and Privacy, 7(2), 77-90.
Kortylewski, A., et al. (2018). Generative adversarial networks for robust facial recognition systems. IEEE Transactions on Neural Networks, 29(8), 1345–1357.
Kumar, A. (2023). Pragmatism in research: A combination of positivism and interpretivism. Journal of Research Methodology, 28(3), 15-29.
Lasker, H. (2024). Privacy and ethical implications of AI-enhanced facial recognition technology. Journal of AI and Society, 19(1), 55-71.
Lasker, M. (2024). Ethical challenges of AI in education: Balancing innovation and privacy. Journal of Ethics and Technology, 12(1), 34-47.
Linkon, A. A., et al. (2024). Generative AI's impact on business applications. Journal of Business Research, 72(1), 99-107.
Linkon, A. A., Johnson, P., & Lee, T. (2024). Advancements in generative models: Transforming industries with AI-driven innovation. International Journal of Emerging Technologies, 18(3), 67–79.
Linkon, M., et al. (2024). Generative AI and its applications in multimodal systems. AI & Society, 29(2), 89–112.
Marriott, M., Montillo, A., & Urban, G. (2020). Enhancing facial recognition systems using generative adversarial networks. Journal of Computer Vision and Image Processing, 11(2), 301-321.
Meden, B., Bano, S., & Baccouche, M. (2021). Privacy-enhancing face biometrics: Balancing utility and individual rights. IEEE Transactions on Information Forensics and Security, 16(8), 4038-4051.
Morande, M. (2023). Evaluating the competencies and limitations of generative AI systems: A survey. Journal of AI Research, 22(4), 132-145.
Napanda, K., & Amadi, J. (2015). Intrusion detection in cyber-physical systems: Current state and future trends. Journal of Cybersecurity and Information Systems, 3(4), 210-225.
Richa Singh, R., et al. (2020). Addressing physical and digital adversarial attacks in facial recognition systems. Journal of Security and Privacy Research, 14(4), 85-99.
Roundtree, D. (2021). Ethical challenges in AI-enhanced facial recognition: User-centered design and guidelines. Journal of Ethics and Technology, 14(3), 201-215.
Saez-Trigueros, D., Elashkar, E. E., & Bourlai, T. (2018). Face recognition using synthetic data.
Saez-Trigueros, D., et al. (2018). Generative adversarial networks for facial recognition. Journal of AI and Data Science, 19(5), 77-90.
Saez-Trigueros, D., et al. (2018). Synthetic image generation using GANs for deep learning applications. Neural Processing Letters, 47(2), 67–85.
Santoso, W., Kumar, R., & Park, J. (2024). Ethical considerations in AI-driven facial recognition systems. Journal of Ethics in Artificial Intelligence, 19(1), 25–42.
Şener, S., & Ergen, B. (2023). Enhancing facial recognition with advanced 3D morphable models. Computer Vision and Pattern Recognition, 25(2), 150-165.
Siedlecki, S. L. (2020). Research methodologies and their practical applications in healthcare. Journal of Nursing Scholarship, 52(3), 243–252.
Siva Sai, M., Jayanthi, K., & Pradeep, M. (2024). The dual role of Generative AI in cybersecurity. Journal of Cybersecurity Research, 20(1), 99-114.
Zhang, J., Liu, X., & Xu, Y. (2023). Regulatory frameworks for ethical AI: Challenges in the African context. Journal of AI Governance, 14(1), 51-65.
Zhou, X., Wang, H., & Li, Y. (2023). Generative adversarial networks for facial recognition: Challenges and opportunities. Journal of Artificial Intelligence Research, 47(2), 128–150.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 West African Journal of Open and Flexible Learning
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
