Real-Time face recognition mobile application for class attendance
In every education setting in Malaysia, there are growing concerns regarding the student attendance-taking process. Currently, the paper-and-pen attendance-taking method is not only time-consuming and inaccurate but also susceptible to impersonation. Thus, the tediousness of manual attendance-taking...
| Main Author: | |
|---|---|
| Format: | Final Year Project / Dissertation / Thesis |
| Published: |
2022
|
| Subjects: | |
| Online Access: | http://eprints.utar.edu.my/4650/ http://eprints.utar.edu.my/4650/1/fyp_CS_2022_TJMQ.pdf |
| _version_ | 1848886206393221120 |
|---|---|
| author | Tham, Jacynth Ming Quan |
| author_facet | Tham, Jacynth Ming Quan |
| author_sort | Tham, Jacynth Ming Quan |
| building | UTAR Institutional Repository |
| collection | Online Access |
| description | In every education setting in Malaysia, there are growing concerns regarding the student attendance-taking process. Currently, the paper-and-pen attendance-taking method is not only time-consuming and inaccurate but also susceptible to impersonation. Thus, the tediousness of manual attendance-taking not only burdens teachers with extra workloads, but also indirectly deteriorates the quality of the lesson delivered. Moreover, the existing face recognition systems developed to conquer this issue are futile due to their sluggish recognition and inability to distinguish between identical siblings effectively.
Hence, this paper describes a novel implementation of a face recognition mobile application named FaceIt, that automates the attendance-taking process in classrooms altogether. The implemented setup requires a basic Android smartphone and a tripod to have a real-time video stream fed automatically into the detection and recognition pipeline within the mobile application itself. The face detection process is then executed using Firebase ML Kit Face Detection API and the face recognition process after that is realized with the use of an enhanced mobile application deep-learning TensorFlow Lite model called MobileFaceNet. The application implemented in this paper is unique compared to other face recognition class attendance applications in the market due to this application’s ability to provide a fallback flow to handle identical siblings, something that most, if not all face recognition models in the market are having difficulties with. Furthermore, Firebase Cloud Database is used to sync all the application’s data across multiple devices within the same educational institution.
The novelty of the developed application is to provide a fully automated attendance taking process in classrooms, with minimal human intervention required only to counteract the vulnerabilities of the face recognition model when presented with identical siblings. The developed application aims to replace the current attendance-taking systems in educational institutions with improved recognition, faster performance time and added convenience for both students and teachers. |
| first_indexed | 2025-11-15T19:34:48Z |
| format | Final Year Project / Dissertation / Thesis |
| id | utar-4650 |
| institution | Universiti Tunku Abdul Rahman |
| institution_category | Local University |
| last_indexed | 2025-11-15T19:34:48Z |
| publishDate | 2022 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | utar-46502023-01-15T13:23:59Z Real-Time face recognition mobile application for class attendance Tham, Jacynth Ming Quan Q Science (General) T Technology (General) In every education setting in Malaysia, there are growing concerns regarding the student attendance-taking process. Currently, the paper-and-pen attendance-taking method is not only time-consuming and inaccurate but also susceptible to impersonation. Thus, the tediousness of manual attendance-taking not only burdens teachers with extra workloads, but also indirectly deteriorates the quality of the lesson delivered. Moreover, the existing face recognition systems developed to conquer this issue are futile due to their sluggish recognition and inability to distinguish between identical siblings effectively. Hence, this paper describes a novel implementation of a face recognition mobile application named FaceIt, that automates the attendance-taking process in classrooms altogether. The implemented setup requires a basic Android smartphone and a tripod to have a real-time video stream fed automatically into the detection and recognition pipeline within the mobile application itself. The face detection process is then executed using Firebase ML Kit Face Detection API and the face recognition process after that is realized with the use of an enhanced mobile application deep-learning TensorFlow Lite model called MobileFaceNet. The application implemented in this paper is unique compared to other face recognition class attendance applications in the market due to this application’s ability to provide a fallback flow to handle identical siblings, something that most, if not all face recognition models in the market are having difficulties with. Furthermore, Firebase Cloud Database is used to sync all the application’s data across multiple devices within the same educational institution. The novelty of the developed application is to provide a fully automated attendance taking process in classrooms, with minimal human intervention required only to counteract the vulnerabilities of the face recognition model when presented with identical siblings. The developed application aims to replace the current attendance-taking systems in educational institutions with improved recognition, faster performance time and added convenience for both students and teachers. 2022-03-02 Final Year Project / Dissertation / Thesis NonPeerReviewed application/pdf http://eprints.utar.edu.my/4650/1/fyp_CS_2022_TJMQ.pdf Tham, Jacynth Ming Quan (2022) Real-Time face recognition mobile application for class attendance. Final Year Project, UTAR. http://eprints.utar.edu.my/4650/ |
| spellingShingle | Q Science (General) T Technology (General) Tham, Jacynth Ming Quan Real-Time face recognition mobile application for class attendance |
| title | Real-Time face recognition mobile application for class attendance
|
| title_full | Real-Time face recognition mobile application for class attendance
|
| title_fullStr | Real-Time face recognition mobile application for class attendance
|
| title_full_unstemmed | Real-Time face recognition mobile application for class attendance
|
| title_short | Real-Time face recognition mobile application for class attendance
|
| title_sort | real-time face recognition mobile application for class attendance |
| topic | Q Science (General) T Technology (General) |
| url | http://eprints.utar.edu.my/4650/ http://eprints.utar.edu.my/4650/1/fyp_CS_2022_TJMQ.pdf |