Implementasi Algoritma YOLOv5 DAN Support Vector Machine untuk Face Recognition Sistem Presensi Mahasiswa

Priambodo, Achmad Rozy (2025) Implementasi Algoritma YOLOv5 DAN Support Vector Machine untuk Face Recognition Sistem Presensi Mahasiswa. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 21081010070-cover.pdf Download (1MB)
	Text (Bab 1) 21081010070-bab1.pdf Download (223kB)
	Text (Bab 2) 21081010070-bab2.pdf Restricted to Repository staff only until 5 December 2027. Download (1MB) \| Request a copy
	Text (Bab 3) 21081010070-bab3.pdf Restricted to Repository staff only until 5 December 2027. Download (864kB) \| Request a copy
	Text (Bab 4) 21081010070-bab4.pdf Restricted to Repository staff only until 5 December 2027. Download (1MB) \| Request a copy
	Text (Bab 5) 21081010070-bab5.pdf Download (241kB)
	Text (Daftar Pustaka) 21081010070-daftarpustaka.pdf Download (199kB)
	Text (Lampiran) 21081010070-lampiran.pdf Restricted to Repository staff only Download (245kB) \| Request a copy

Abstract

This research aims to implement a combination of the You Only Look Once version 5 (YOLOv5) algorithm and Support Vector Machine (SVM) for a face recognition-based student attendance system. The integration of these methods is expected to improve both accuracy and efficiency compared to conventional attendance systems. The research stages include collecting student face datasets from 15-second video recordings, performing preprocessing, detecting faces using YOLOv5, extracting features with Histogram of Oriented Gradients (HOG), and classifying them using SVM. The experimental results show that the YOLOv5 and SVM combination achieves up to 98% face recognition accuracy at a normal angle (0°) and remains stable above 90% at up to 55° angle variations. Furthermore, the developed face recognition attendance system reduces attendance time to an average of 6 minutes for 50 students, compared to 13 minutes with manual methods. Therefore, integrating YOLOv5 and SVM is proven to be an effective approach to enhance the speed and accuracy of face recognition-based attendance systems.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Junaidi, Achmad	NIDN0710117803	achmadjunaidi.if@upnjatim.ac.id
Thesis advisor	Al Haromainy, Muhammad Muharrom	NIDN0701069503	muhammad.muharrom.if@upnjatim.ac.id

Subjects:

Q Science > QA Mathematics > QA76.6 Computer Programming
T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Achmad Rozy Priambodo

Date Deposited:

05 Dec 2025 07:59

Last Modified:

05 Dec 2025 07:59

URI:

https://repository.upnjatim.ac.id/id/eprint/48053