PENGENALAN PLAT NOMOR KENDARAAN MENGGUNAKAN DEEP LEARNING BERDASARKAN CITRA BERGERAK PADA JALAN TOL

BRILIAWAN, CATUR RIZKI and Fachrurrozi, Muhammad (2023) PENGENALAN PLAT NOMOR KENDARAAN MENGGUNAKAN DEEP LEARNING BERDASARKAN CITRA BERGERAK PADA JALAN TOL. Undergraduate thesis, Sriwijaya University.

[thumbnail of RAMA_55201_09021381924097.pdf] Text
RAMA_55201_09021381924097.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (3MB) | Request a copy
[thumbnail of RAMA_55201_09021381924097_TURNITIN.pdf] Text
RAMA_55201_09021381924097_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (10MB) | Request a copy
[thumbnail of RAMA_55201_09021381924097_0222058001_01_front_ref.pdf] Text
RAMA_55201_09021381924097_0222058001_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (5MB)
[thumbnail of RAMA_55201_09021381924097_0222058001_02.pdf] Text
RAMA_55201_09021381924097_0222058001_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (2MB) | Request a copy
[thumbnail of RAMA_55201_09021381924097_0222058001_03.pdf] Text
RAMA_55201_09021381924097_0222058001_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy
[thumbnail of RAMA_55201_09021381924097_0222058001_04.pdf] Text
RAMA_55201_09021381924097_0222058001_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (4MB) | Request a copy
[thumbnail of RAMA_55201_09021381924097_0222058001_05.pdf] Text
RAMA_55201_09021381924097_0222058001_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (3MB) | Request a copy
[thumbnail of RAMA_55201_09021381924097_0222058001_06.pdf] Text
RAMA_55201_09021381924097_0222058001_06.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (294kB) | Request a copy
[thumbnail of RAMA_55201_09021381924097_0222058001_07_ref.pdf] Text
RAMA_55201_09021381924097_0222058001_07_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (422kB) | Request a copy
[thumbnail of RAMA_55201_09021381924097_0222058001_08_lamp.pdf] Text
RAMA_55201_09021381924097_0222058001_08_lamp.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (933kB) | Request a copy

Abstract

Vehicle License Plate Pattern Recognition is a critical component in traffic monitoring systems, parking security, and various other applications. In this research, we propose a vehicle license plate pattern recognition system that combines YOLOv7 (You Only Look Once version 7) as an object detector and TesseractOCR as a text character recognizer. Under these conditions, researchers developed software to recognize vehicle license plate patterns from moving images using the YOLOv7 method and TesseractOCR to identify characters on the license plate, making it easier for officers to recognize vehicle plates. TesseractOCR, a powerful Optical Character Recognition (OCR) engine, is used to recognize text characters on the license plates. TesseractOCR has the capability to recognize various font styles and languages, making it an ideal choice for character recognition on diverse vehicle plates. The testing results of the proposed system showed good accuracy, even in complex situations. The software was builtusing four combinations of Epoch and batch size, namely Batch 16 Epoch 50, Batch 16 Epoch 100, Batch 16 Epoch 250, and Batch 16 Epoch 500 to obtain trained models for the testing process. The testing process was carried out directly using moving images. The accuracy achieved was 80%, with a precision of 87.5%and a recall of 90.3%. This system has significant potential for use in various applications such as traffic monitoring and vehicle security

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Pengenalan Pola, YOLOv7, TesseractOCR, Citra Bergerak
Subjects: Q Science > QA Mathematics > QA75-76.95 Calculating machines > QA76 Computer software
Q Science > QA Mathematics > QA8.9-QA10.3 Computer science. Artificial intelligence. Computational complexity. Data structures (Computer scienc. Mathematical Logic and Formal Languages
Divisions: 09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User: Catur Rizki Briliawan
Date Deposited: 23 Nov 2023 07:07
Last Modified: 23 Nov 2023 07:07
URI: http://repository.unsri.ac.id/id/eprint/130932

Actions (login required)

View Item View Item