PERANCANGAN DAN IMPLEMENTASI MODEL DETEKSI WAJAH SEDERHANA DENGAN METODE MOBILENET V3 DAN MTCNN

RYADHI, MASAGUS MUHAMMAD FAZRI SAFIQ and Ubaya, Huda (2021) PERANCANGAN DAN IMPLEMENTASI MODEL DETEKSI WAJAH SEDERHANA DENGAN METODE MOBILENET V3 DAN MTCNN. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011381722086.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
	Text RAMA_56201_09011381722086_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (23MB) | Request a copy
Preview	Text RAMA_56201_09011381722086_0216068101_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) | Preview
	Text RAMA_56201_09011381722086_0216068101_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (783kB) | Request a copy
	Text RAMA_56201_09011381722086_0216068101_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (496kB) | Request a copy
	Text RAMA_56201_09011381722086_0216068101_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011381722086_0216068101_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (34kB) | Request a copy
	Text RAMA_56201_09011381722086_0216068101_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (153kB) | Request a copy
	Text RAMA_56201_09011381722086_0216068101_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (983kB) | Request a copy

Abstract

The research in this final task report, which is how to design a face date application using CNN's Multi-Task method and compare it with the MobileNet-V3 method. Testing was conducted between CNN Multi-Task and MobileNet V3 by bilingating faces at every angle using the camera and compared to wearing masks and not wearing masks. . Face detection experiments conducted, CNN Multi-Task method can perform good face detection by doing a number of conditions. When not using accessories can detect all faces well, and at the time of using accessories can only detect 10 out of 20 while on face detection using mobilenet V3 method when not using the mask can also detect the entire face correctly while at the time of using the mask can detect 18 out of 20 faces.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Face detection, Covolution Neural Network , Multi-Task CNN, MobileNet V3, Deep Learing.
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Users 5637 not found.
Date Deposited:	06 Aug 2021 01:32
Last Modified:	06 Aug 2021 01:32
URI:	http://repository.unsri.ac.id/id/eprint/51734

Actions (login required)

View Item