IMPLEMENTASI MODEL EUM PADA FACENET UNTUK PENGENALAN WAJAH BERMASKER

NOORFAJR, MUHAMMAD IVAN and Supardi, Julian and Rizqie, Muhammad Qurhanul (2022) IMPLEMENTASI MODEL EUM PADA FACENET UNTUK PENGENALAN WAJAH BERMASKER. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021281722048.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
Preview	Text RAMA_55201_09021281722048_001077210_0203128701_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) | Preview
	Text RAMA_55201_09021281722048_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (5MB) | Request a copy
	Text RAMA_55201_09021281722048_001077210_0203128701_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (393kB) | Request a copy
	Text RAMA_55201_09021281722048_001077210_0203128701_03.pdf - Published Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (282kB) | Request a copy
	Text RAMA_55201_09021281722048_001077210_0203128701_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021281722048_001077210_0203128701_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (354kB) | Request a copy
	Text RAMA_55201_09021281722048_001077210_0203128701_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (92kB) | Request a copy
	Text RAMA_55201_09021281722048_001077210_0203128701_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (145kB) | Request a copy
	Text RAMA_55201_09021281722048_001077210_0203128701_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (238kB) | Request a copy

Abstract

The emergence of the COVID-19 virus has made facial recognition systems less effective in recognizing faces with masks. To overcome this, the author use the method proposed by Fadi Boutros named Unmasked Embedding Model (EUM) and the Self-restraint Triplet Loss loss function to improve the accuracy of the FaceNet facial recognition model. In this study, the accuracy level of the EUM model using the KomNet embedding dataset extracted using a FaceNet model that is not trained to recognize masked faces has an accuracy value of 0.6974 and a loss value of 1.256. Meanwhile, the FaceNet model that is trained to recognize masked faces gets an accuracy value of 0.7763 and a loss value of 0.7293.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Pengenalan Pola, Deep Learning, Pengenalan Wajah Bermasker, FaceNet, Embedding Unmasked Model, Triplet Loss
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Muhammad Ivan Noorfajr
Date Deposited:	27 Sep 2022 05:36
Last Modified:	27 Sep 2022 05:36
URI:	http://repository.unsri.ac.id/id/eprint/79993

Actions (login required)

View Item