Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{209418,
        author = {Joga Akhil and Kuda Nageswara Rao},
        title = {E-Authentication System Using Face Recognition with Spring Boot},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {5},
        pages = {1719-1726},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=209418},
        abstract = {Password- and token-based authentication remain exposed to credential reuse, phishing and loss, whereas face recognition offers a contactless alternative that needs only a commodity camera. This paper presents AJFace, an e-authentication system built as three independently deployable services: a Java 21 / Spring Boot 3 backend that issues JSON Web Tokens and enforces role-based and object-level access control; a Python / FastAPI AI service that performs detection and recognition with the InsightFace toolkit (RetinaFace detector, ArcFace 512-dimensional embeddings, cosine-similarity search); and a React single-page frontend. The AI service contributes a threshold-anchored similarity-to-confidence rescaling that keeps its decision rule and the backends’ rule in agreement, an enrolment-time duplicate-identity check, and an image-quality and heuristic liveness screen that is documented as a placeholder rather than a trained anti-spoofing model. The system is exercised through an enterprise attendance case study in which one face-verification event both authenticates the user and records attendance, supported by leave, payroll, alerting and reporting modules. Twenty-two automated component tests of the AI service pass, and a functional walkthrough of the running prototype confirms the main workflows. No large-scale false-acceptance/false-rejection or latency benchmark was performed; the paper states these limitations explicitly, together with directions for future work.},
        keywords = {face recognition, e-authentication, ArcFace, Spring Boot, microservices, JSON Web Token.},
        month = {October},
        }