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{197885,
        author = {ADISHARLAPALLI SOHAN PRASAD and CHEVVAKULA SIRI LALITHA and BAIRI VAMSHIKA and BOLLA VENKATESH and G. Srinivasa Rao},
        title = {WEB BASED FACIAL AUTHENTICATION FOR LOGIN},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {7342-7352},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=197885},
        abstract = {Traditional password-based authentication systems are increasingly vulnerable to phishing attacks, credential theft, and usability limitations, making them unsuitable for modern secure applications. As an alternative, biometric authentication—particularly facial recognition—has gained significant attention due to its convenience and higher resistance to credential-based attacks. However, existing facial authentication systems still face critical challenges, including susceptibility to presentation attacks (spoofing), reduced accuracy in distinguishing highly similar faces, and scalability limitations in large-scale identity matching. This work presents a secure web-based facial authentication system designed as a fully password less identity verification framework. The system extracts high-dimensional facial feature representations using deep learning-based embedding techniques that map facial images into a discriminative vector space for reliable identity comparison. To ensure scalability and fast identity retrieval, the system performs efficient similarity-based matching in a high-dimensional feature space, enabling rapid verification even in large user databases. To address security vulnerabilities, a dynamic active liveness detection mechanism is incorporated, which uses real-time behavioral and motion-based challenges to confirm the physical presence of a live user and effectively mitigate spoofing attempts using static images or pre-recorded videos. The proposed system further enhances robustness against highly similar facial structures by applying strict similarity thresholds for identity verification. A practical implementation is demonstrated through integration with a web application, replacing traditional login mechanisms with a seamless biometric authentication flow.},
        keywords = {Facial Recognition, Biometric Authentication, Deep Learning, Face Embeddings, Liveness Detection, Anti-Spoofing, Password less Authentication, Identity Verification, Feature Space Matching, Web Security.},
        month = {April},
        }