DETEKSI PLAT NOMOR KENDARAAN BERBASIS ALGORITMA YOLO

RINALDIANSYAH, RANGGA and Dwijayanti, Suci (2020) DETEKSI PLAT NOMOR KENDARAAN BERBASIS ALGORITMA YOLO. Undergraduate thesis, Sriwijaya University.

	Text RAMA_20201_03041381821009.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
	Text RAMA_20201_03041381821009_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
Preview	Text RAMA_20201_03041381821009_0030078404_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (946kB) | Preview
	Text RAMA_20201_03041381821009_0030078404_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (443kB) | Request a copy
	Text RAMA_20201_03041381821009_0030078404_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (174kB) | Request a copy
	Text RAMA_20201_03041381821009_0030078404_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_20201_03041381821009_0030078404_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (35kB) | Request a copy
	Text RAMA_20201_03041381821009_0030078404_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (73kB) | Request a copy
	Text RAMA_20201_03041381821009_0030078404_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy

Abstract

In Indonesias, vehicle number plate detection system as yet employs human labor such as in the parking system. Thus, an automatic vehicle number plate detection system is required to replace the manual system. In addition, some proposed methods to detect vehicle number plate license may have low accuracy because they depend on the extracted feature performed before the classification. Hence, this work develops an automatic vehicle number plate detection system based on YOLO algorithm. The data used consist of 952 data obtained from CCTV and smartphone camera, and 500 images of vehicle number plate obtained from internet to increase divergence while training YOLO. The results showed that the Yolov2-tiny-voc model using learning rate 1e-05 in 100 epochs (1500 steps) can be implemented to detect vehicle number plates in images and real-time video. Using the trained YOLO model, testing results showed that 174 vehicle number plates from 200 images can be detected with an accuracy of 87%. While in real-time video, the proposed YOLO model may detect vehicle number plate well with the average accuracy of 100% and the obtained confidence value were varied depend on lighting, vehicle type, and ambient conditions. Keyword : Vehicle Plate Detection, YOLO Algorithm, Accuracy.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Deteksi Plat Kendaraan, Algoritma YOLO, Akurasi.
Subjects:	Q Science > QA Mathematics > QA1-939 Mathematics > QA37.3.1.64 Applied Mathematics T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK1-9971 Electrical engineering. Electronics. Nuclear engineering > TK1 Electrical engineering--Periodicals. Automatic control--Periodicals. Computer science--Periodicals. Information technology--Periodicals. Automatic control. Computer science. Electrical engineering. Information technology.
Divisions:	03-Faculty of Engineering > 20201-Electrical Engineering (S1)
Depositing User:	Users 6221 not found.
Date Deposited:	25 Jun 2020 06:28
Last Modified:	25 Jun 2020 06:28
URI:	http://repository.unsri.ac.id/id/eprint/30758

Actions (login required)

View Item