Smart attendance system with Iot based face recognition using deep learning approach
Attendance management system is an indispensable practice in which every institution or organisation adopts to mark the attendance of their employees or members. The manual process of marking attendance by using a paper-based or file-based system is riddled with flaws such as the risk of information...
| Main Author: | |
|---|---|
| Format: | Final Year Project / Dissertation / Thesis |
| Published: |
2023
|
| Subjects: | |
| Online Access: | http://eprints.utar.edu.my/5821/ http://eprints.utar.edu.my/5821/1/MH_1803927_Final_SEAH_YOU.pdf |
| _version_ | 1848886513903861760 |
|---|---|
| author | Seah, You |
| author_facet | Seah, You |
| author_sort | Seah, You |
| building | UTAR Institutional Repository |
| collection | Online Access |
| description | Attendance management system is an indispensable practice in which every institution or organisation adopts to mark the attendance of their employees or members. The manual process of marking attendance by using a paper-based or file-based system is riddled with flaws such as the risk of information loss, falsification or disasters. The current norm delineates the deployment of smart attendance system using RFID tags, fingerprints, iris scans, voice recognition, etc. Nowadays, technological developments propagate the practical utilisation of face recognition approach for a more efficient attendance management system. The face recognition-based attendance system is convenient with additional advantages that it can avoid human intervention and thus assisting to control the spread of viruses. In this project, a real-time attendance management system that employs face recognition approach is proposed to recognize individuals. Two face recognition models were developed: the first model used Deep Neural Network (DNN) for face detection, FaceNet for feature extraction, and Support Vector Machine (SVM) for face classification, and the second model utilised Convolutional Neural Network, specifically the trained VGG16 model, with the ImageNet dataset as its pretrained weights. Transfer learning was employed to apply the pretrained network for recognizing faces. The proposed systems’ effectiveness was demonstrated through a comparison of both face recognition models, and the first model with testing accuracy of 97.62 % was integrated into a designated graphical user interface (GUI). In conclusion, the project’s aim and objectives were successfully accomplished, which included developing a facial recognition system designed specifically for attendance tracking and conducting a literature review covering current approaches and results in facial recognition algorithms. Furthermore, the GUI with essential features such as creating new databases, face recognition, and attendance monitoring for users was developed to ease attendance monitoring for end-users. The system’s performance and usability were analyzed to provide insights for future enhancements. |
| first_indexed | 2025-11-15T19:39:42Z |
| format | Final Year Project / Dissertation / Thesis |
| id | utar-5821 |
| institution | Universiti Tunku Abdul Rahman |
| institution_category | Local University |
| last_indexed | 2025-11-15T19:39:42Z |
| publishDate | 2023 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | utar-58212023-08-08T14:29:25Z Smart attendance system with Iot based face recognition using deep learning approach Seah, You TJ Mechanical engineering and machinery Attendance management system is an indispensable practice in which every institution or organisation adopts to mark the attendance of their employees or members. The manual process of marking attendance by using a paper-based or file-based system is riddled with flaws such as the risk of information loss, falsification or disasters. The current norm delineates the deployment of smart attendance system using RFID tags, fingerprints, iris scans, voice recognition, etc. Nowadays, technological developments propagate the practical utilisation of face recognition approach for a more efficient attendance management system. The face recognition-based attendance system is convenient with additional advantages that it can avoid human intervention and thus assisting to control the spread of viruses. In this project, a real-time attendance management system that employs face recognition approach is proposed to recognize individuals. Two face recognition models were developed: the first model used Deep Neural Network (DNN) for face detection, FaceNet for feature extraction, and Support Vector Machine (SVM) for face classification, and the second model utilised Convolutional Neural Network, specifically the trained VGG16 model, with the ImageNet dataset as its pretrained weights. Transfer learning was employed to apply the pretrained network for recognizing faces. The proposed systems’ effectiveness was demonstrated through a comparison of both face recognition models, and the first model with testing accuracy of 97.62 % was integrated into a designated graphical user interface (GUI). In conclusion, the project’s aim and objectives were successfully accomplished, which included developing a facial recognition system designed specifically for attendance tracking and conducting a literature review covering current approaches and results in facial recognition algorithms. Furthermore, the GUI with essential features such as creating new databases, face recognition, and attendance monitoring for users was developed to ease attendance monitoring for end-users. The system’s performance and usability were analyzed to provide insights for future enhancements. 2023 Final Year Project / Dissertation / Thesis NonPeerReviewed application/pdf http://eprints.utar.edu.my/5821/1/MH_1803927_Final_SEAH_YOU.pdf Seah, You (2023) Smart attendance system with Iot based face recognition using deep learning approach. Final Year Project, UTAR. http://eprints.utar.edu.my/5821/ |
| spellingShingle | TJ Mechanical engineering and machinery Seah, You Smart attendance system with Iot based face recognition using deep learning approach |
| title | Smart attendance system with Iot based face recognition using deep learning approach |
| title_full | Smart attendance system with Iot based face recognition using deep learning approach |
| title_fullStr | Smart attendance system with Iot based face recognition using deep learning approach |
| title_full_unstemmed | Smart attendance system with Iot based face recognition using deep learning approach |
| title_short | Smart attendance system with Iot based face recognition using deep learning approach |
| title_sort | smart attendance system with iot based face recognition using deep learning approach |
| topic | TJ Mechanical engineering and machinery |
| url | http://eprints.utar.edu.my/5821/ http://eprints.utar.edu.my/5821/1/MH_1803927_Final_SEAH_YOU.pdf |