Novoselik, Dwiki Christianto (2025) Implementasi Face Recognition Untuk System Absensi Berbasis Website Pada Lingkungan Akademik : Studi Kasus Di Politeknik Negeri Bali. Undergraduate thesis, Politeknik Negeri Bali.

[thumbnail of Full Text] Text (Full Text)
RAMA_58302_2115354087_full.pdf - Accepted Version
Restricted to Repository staff only
Download (14MB) | Request a copy
[thumbnail of Cover, Bab 1, Bab 5 dan Referensi] Text (Cover, Bab 1, Bab 5 dan Referensi)
RAMA_58302_2115354087_0031058002_ 0817128601_part.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (389kB) | Request a copy
[thumbnail of iThenticate] Text (iThenticate)
RAMA_58302_2115354087_iThenticate.pdf - Accepted Version
Restricted to Repository staff only
Download (4MB) | Request a copy

Abstract

The implementation of an accurate and efficient attendance system is essential in academic environments to improve discipline and streamline attendance recording. This research aims to develop a web-based attendance system using facial recognition technology, with a case study conducted at Politeknik Negeri Bali. The system utilizes the Multi-task Cascaded Convolutional Network (MTCNN) for face detection, FaceNet for generating facial embeddings, and Support Vector Machine (SVM) as the classification algorithm for student identification. The recognition process is performed in real-time through a camera, where detected faces are compared to pre-stored embeddings in the system. If the similarity (confidence) exceeds the defined threshold, the system automatically records the student's attendance. The backend is developed using FastAPI, while the user interface is built using Laravel and other web technologies. Implementation results show that the system can recognize student faces with high accuracy under varying lighting conditions and facial angles. Testing was carried out using black-box methods and performance evaluation was based on metrics such as accuracy, precision, recall, f1-score, and confusion matrix. This study is expected to serve as an alternative solution for modernizing attendance systems in higher education institutions.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Face Recognition, FaceNet, SVM, Attendance System, FastAPI, Bali State of Polytechnic
Subjects: Ilmu Teknik > Teknik Elektro Dan Informatika > Teknologi Informasi
Divisions: Jurusan Teknologi Informasi > Prodi D4 Teknologi Rekayasa Perangkat Lunak > Skripsi
Depositing User: Dwiki Christianto Novoselik
Date Deposited: 13 Sep 2025 03:48
Last Modified: 13 Sep 2025 03:48
URI: https://repository.pnb.ac.id/id/eprint/18538

Actions (login required)

View Item View Item