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{206580,
        author = {Abdul Shafiq and Dhanush Udaya Acharya and Sudithraj S Shetty and Sujal M Naik and Ms. Abhijnha B N},
        title = {Smart Attend: Face Recognition Attendance System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {no},
        pages = {1-8},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=206580},
        abstract = {This smart system based on Automated Facial Recognition (AFC) not only suffers from significant security threats and privacy issues regarding storing facial images but also requires powerful Graphic Processing Units (GPU). Thus, the aim of the present paper is to develop a Smart Classroom Attendance System based on CPU, which will be able to process images with the help of standard hardware while meeting privacy concerns at the same time. Multi-Task Cascaded Convolutional Networks (MTCNN) are used to detect and align the face. After that, FaceNet (InceptionResnetV1) generates 512-dimensions features from the face image. In order to verify possible spoofs of attendance system, a function of liveness check via MediaPipe Face Mesh measures Eye Aspect Ratio (EAR) to establish if the student blinks. The proposed system does not rely on comparing an image to a single picture but utilizes a decision engine, where the cosine similarity threshold is 0.70 or greater for a sequence of at least three consecutive matching images of a person. It is not a video, which is recorded but non-reversible numerical values of the face image are used as embeddings. According to experimental data, processing time of each frame varies from 100 to 200 milliseconds, making detection very accurate.},
        keywords = {Biometric authentication, Face embeddings, Facial recognition, Liveness detection, Smart classroom attendance system},
        month = {July},
        }