PENGENALAN WAJAH BERMASKER SECARA REAL-TIME MENGGUNAKAN METODE YOLOv5

PAKOMGAN, RAFLY and Fachrurrozi, Muhammad and Primanita, Anggina (2022) PENGENALAN WAJAH BERMASKER SECARA REAL-TIME MENGGUNAKAN METODE YOLOv5. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021381924102.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (11MB) | Request a copy
	Text RAMA_55201_09021381924102_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (21MB) | Request a copy
Preview	Text RAMA_55201_09021381924102_0222058001_0206088901_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (938kB) | Preview
	Text RAMA_55201_09021381924102_0222058001_0206088901_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (449kB) | Request a copy
	Text RAMA_55201_09021381924102_0222058001_0206088901_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (291kB) | Request a copy
	Text RAMA_55201_09021381924102_0222058001_0206088901_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (568kB) | Request a copy
	Text RAMA_55201_09021381924102_0222058001_0206088901_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021381924102_0222058001_0206088901_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (30kB) | Request a copy
	Text RAMA_55201_09021381924102_0222058001_0206088901_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (160kB) | Request a copy
	Text RAMA_55201_09021381924102_0222058001_0206088901_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy

Abstract

The government requires people to wear face masks to reduce the transmission of the COVID-19 virus. Face recognition system becomes less effective at recognizing masked faces. In this research, a software is developed to recognize masked face in real-time using the YOLOv5 method. Training of the model was done with 9 different configurations of epoch and batch size, of which the best result was taken and used for testing. Testing was done using images and real-time input. The maximum accuracy of identification using image is 100% while the maximum accuracy of real-time identification is 64%. While running the experiment, it is found that the brightness of the room affects the performance of YOLOv5. When the brightness is drastically different, it is more difficult to identify the individual.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Pengenalan Wajah, Wajah Bermasker, YOLOv5, Real-Time
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation. T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Rafly Pakomgan
Date Deposited:	20 Jan 2023 03:01
Last Modified:	20 Jan 2023 03:01
URI:	http://repository.unsri.ac.id/id/eprint/87125

Actions (login required)

View Item