DZAKWAN, DAFFA ARIF (2026) IMPLEMENTASI FACE RECOGNITION BERBASIS FACENET DENGAN ANTI-SPOOFING PADA SISTEM ABSENSI MOBILE SIWIRA. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
Cover.pdf Download (818kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
Bab 1.pdf Restricted to Registered users only Download (222kB) |
|
|
Text (BAB II)
Bab 2.pdf Restricted to Registered users only Download (323kB) |
|
|
Text (BAB III)
Bab 3.pdf Restricted to Registered users only Download (279kB) |
|
|
Text (BAB IV)
Bab 4.pdf Restricted to Registered users only Download (1MB) |
|
|
Text (BAB V)
Bab 5.pdf Restricted to Registered users only Download (208kB) |
|
|
Text (DAFTAR PUSTAKA)
Daftar Pustaka.pdf Restricted to Registered users only Download (131kB) |
|
|
Text (LAMPIRAN)
Lampiran.pdf Restricted to Registered users only Download (843kB) |
Abstract
The attendance process in one of the operational units of PT Wira Sandi is still conducted manually, making it prone to recording errors, delays in data recapitulation, and the potential for fraud, such as proxy attendance. Furthermore, the attendance system is not yet supported by an identity verification mechanism based on Face Recognition and Anti-Spoofing to ensure that attendance is marked by the respective employee. Leave administration is also still managed manually, rendering the application, approval, recording, and data storage processes inefficient. This study aims to implement FaceNet-based Face Recognition with an Anti-Spoofing mechanism in the SiWira Mobile attendance system, as well as to develop an integrated leave application feature within the application. This study employs a quantitative research method focusing on measuring system performance based on numerical data obtained from implementation testing of Face Recognition and Anti-Spoofing. The test data are classified into True Positive (TP), False Positive (FP), True Negative (TN), and False Negative (FN), and are subsequently arranged in a Confusion Matrix to calculate Accuracy, Precision, Recall, F1-Score, and Error Rate as performance indicators of the system. The testing results across 25 scenarios demonstrate an Accuracy of 92%, Precision of 97,73%, Recall of 86%, and F1-Score of 91,48%. AntiSpoofing testing also indicates that the system is capable of accepting real faces while rejecting the use of photos on devices and conditions without eye blinks. The results show that the implementation of FaceNet-based Face Recognition with an Anti-Spoofing mechanism is able to enhance the security of the attendance process, while the integration of the leave application feature helps improve the effectiveness of the leave administration process. Keyword : Face Recognition, FaceNet, Anti-Spoofing, Attendance System, Leave Application Proses absensi pada salah satu unit operasional PT Wira Sandi masih dilakukan secara manual sehingga rentan terhadap kesalahan pencatatan, keterlambatan rekapitulasi data, serta potensi terjadinya kecurangan, seperti penitipan absensi. Selain itu, sistem absensi belum didukung dengan mekanisme verifikasi identitas berbasis Face Recognition dan Anti-Spoofing untuk memastikan bahwa absensi dilakukan oleh pegawai yang bersangkutan. Administrasi cuti juga masih dilakukan secara manual sehingga proses pengajuan, persetujuan, pencatatan, dan penyimpanan data menjadi kurang efisien. Penelitian ini bertujuan mengimplementasikan Face Recognition berbasis FaceNet dengan mekanisme Anti-Spoofing pada sistem absensi Mobile SiWira serta mengembangkan fitur pengajuan cuti yang terintegrasi dalam aplikasi. Penelitian ini menggunakan metode penelitian kuantitatif yang berfokus pada pengukuran kinerja sistem berdasarkan data numerik hasil pengujian implementasi Face Recognition dan Anti-Spoofing. Data hasil pengujian diklasifikasikan ke dalam True Positive (TP), False Positive (FP), True Negative (TN), dan False Negative (FN), kemudian disusun dalam Confusion Matrix untuk menghitung nilai Accuracy, Precision, Recall, F1- Score, dan Error Rate sebagai indikator performa sistem. Hasil pengujian terhadap 100 skenario menunjukkan nilai Accuracy sebesar 92%, Precision sebesar 97,73%, Recall sebesar 86%, dan F1-Score sebesar 91,48%. Pengujian Anti-Spoofing juga menunjukkan bahwa sistem mampu menerima wajah asli serta menolak penggunaan foto pada perangkat dan kondisi tanpa kedipan mata. Hasil penelitian menunjukkan bahwa implementasi Face Recognition berbasis FaceNet dengan mekanisme Anti-Spoofing mampu meningkatkan keamanan proses absensi, sedangkan integrasi fitur pengajuan cuti membantu meningkatkan efektivitas proses administrasi cuti. Kata Kunci : Face Recognition, FaceNet, Anti-Spoofing, Sistem Absensi, Pengajuan Cuti
| Item Type: | Thesis (S1) |
|---|---|
| NIM/NIDN Creators: | 41822010060 |
| Uncontrolled Keywords: | Face Recognition, FaceNet, Anti-Spoofing, Sistem Absensi, Pengajuan Cuti |
| Subjects: | 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 006 Special Computer Methods/Metode Komputer Tertentu > 006.4 Computer Pattern Recognition/Pola Pengenalan Komputer 700 Arts/Seni, Seni Rupa, Kesenian > 770 Photography and Photographs/Seni Fotografi dan Foto > 771 Techniques and Procedures/Teknik Seni Fotografi dan Foto, Prosedur Seni Fotografi dan Foto > 771.3 Cameras and Accessories/Kamera dan Asesoris Kamera > 771.37 Focusing and Exposure Apparatus/Aparatus Fokus Kamera |
| Divisions: | Fakultas Ilmu Komputer > Sistem Informasi |
| Depositing User: | khalimah |
| Date Deposited: | 17 Sep 2026 01:19 |
| Last Modified: | 17 Sep 2026 01:19 |
| URI: | http://repository.mercubuana.ac.id/id/eprint/103931 |
Actions (login required)
 |
View Item |
