A Facial Biometric Architecture for Pension Administration with Explicit Verification States and Auditable Record Linkage

A facial recognition component becomes useful to pension administration only when its output is connected to a trusted record and a reviewable decision. This study develops a modular architecture for a MATLAB-based pensioner-verification prototype in Enugu North, Nigeria. The method combines analysis of the acquisition and matching callbacks, a formal state model, a record-linkage schema and an evidence assessment of the existing prototype. Camera capture, image processing, feature visualization and ranked-image retrieval are identifiable in the implementation. A local-feature callback attempts to index 20 returned feature pairs before displaying a verification message; its behavior therefore contains a match-count boundary and an exception-dependent decision. The underlying neural-model test matrix records 102 correct classifications among 105 observations, while a separate application table contains 18 True-coded entries among 20 cases. These recognition results are treated as component evidence rather than measurements of database or pension-payment performance. The architecture introduces explicit capture, matching, review and audit states, with stable person identifiers linking templates and service records. The study contributes a formal integration model and a traceable assessment of implemented versus proposed functions. The result is a technically specified route from a recognition prototype to an accountable verification service, with calibration, transactional testing and a monitored institutional pilot required before operational adoption.

biometric information system, pension administration, facial verification, state model, record linkage, software architecture

1. Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. In 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Vol. 1, pp. 886–893). IEEE. https://doi.org/10.1109/CVPR.2005.177 [Google Scholar] [Crossref]

2. Deng, J., Guo, J., Xue, N., & Zafeiriou, S. (2019). ArcFace: Additive angular margin loss for deep face recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 4690–4699). https://openaccess.thecvf.com/content_CVPR 2019/html/Deng_ArcFace Additive Angular_Margin_Loss_for_Deep_Face_Recognition_CVPR_2019_paper.html [Google Scholar] [Crossref]

3. Getreuer, P. (2013). A survey of Gaussian convolution algorithms. Image Processing On Line, 3, 286–310. https://doi.org/10.5201/ipol.2013.87 [Google Scholar] [Crossref]

4. Jain, A. K., Ross, A., & Prabhakar, S. (2004). An introduction to biometric recognition. IEEE Transactions on Circuits and Systems for Video Technology, 14(1), 4–20. https://doi.org/10.1109/TCSVT.2003.818349 [Google Scholar] [Crossref]

5. Kim, M., Jain, A. K., & Liu, X. (2022). AdaFace: Quality adaptive margin for face recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 18750–18759). https://openaccess.thecvf.com/content/CVPR2022/html/Kim AdaFace Quality Adaptive Margin_for_Face_Recognition_CVPR_2022_paper.html [Google Scholar] [Crossref]

6. MathWorks. (n.d.-a). matchFeatures: Find matching features. Retrieved October 17, 2026, from https://www.mathworks.com/help/vision/ref/matchfeatures.html [Google Scholar] [Crossref]

7. MathWorks. (n.d.-b). retrieveImages: Search image set for similar image. Retrieved October 17, 2026, from https://www.mathworks.com/help/vision/ref/retrieveimages.html [Google Scholar] [Crossref]

8. Meng, Q., Zhao, S., Huang, Z., & Zhou, F. (2021). MagFace: A universal representation for face recognition and quality assessment. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 14225–14234). https://openaccess.thecvf.com/content/ CVPR2021/ html/Meng_MagFace_A_Universal_Representation_for_Face_Recognition_and_Quality_Assessment_CVPR_2021_paper.html [Google Scholar] [Crossref]

9. Schroff, F., Kalenichenko, D., & Philbin, J. (2015). FaceNet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 815–823). https://openaccess.thecvf.com/content_cvpr 2015/html/Schroff FaceNet A_Unified_2015_CVPR_paper.html [Google Scholar] [Crossref]

10. Sharma, D., & Selwal, A. (2023). A survey on face presentation attack detection mechanisms: Hitherto and future perspectives. Multimedia Systems, 29, 1527–1577. https://doi.org/10.1007/s00530-023-01070-5 [Google Scholar] [Crossref]

11. Sun, Z., & Liu, Z. (2025). Ensuring privacy in face recognition: A survey on data generation, inference and storage. Discover Applied Sciences, 7, Article 441. https://doi.org/10.1007/s42452-025-06987-2 [Google Scholar] [Crossref]

12. Wang, M., & Deng, W. (2021). Deep face recognition: A survey. Neurocomputing, 429, 215–244. https://doi.org/10.1016/j.neucom.2020.10.081 [Google Scholar] [Crossref]

13. Yu, Z., Liu, A., Zhao, C., Cheng, K. H. M., Cheng, X., & Zhao, G. (2023). Flexible-modal face anti-spoofing: A benchmark. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (pp. 6346–6351). https://openaccess.thecvf.com/content/CVPR2023W/ FAS/html/Yu_Flexible-Modal_Face_Anti-Spoofing_A_Benchmark_CVPRW_2023_paper.html [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet