Perbaikan Kualitas Citra untuk Pengenalan Pelat Nomor Kendaraan pada Data Video Kendaraan Menggunakan Dynamic Histogram Equalization

Maharani, Safhira (2021) Perbaikan Kualitas Citra untuk Pengenalan Pelat Nomor Kendaraan pada Data Video Kendaraan Menggunakan Dynamic Histogram Equalization. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

[img] Text
05111740000027-Undergraduate_Thesis.pdf - Accepted Version
Restricted to Repository staff only until 1 October 2023.

Download (9MB) | Request a copy

Abstract

Teknologi pengenalan pelat nomor kendaraan atau License Plate Recognition (LPR) telah diadopsi di banyak aplikasi lalu lintas modern, seperti tempat parkir, pemantauan lalu lintas, dan kontrol keamanan jalanan. Pada dunia nyata, sistem pengenalan pelat nomor digunakan di berbagai kondisi seperti siang, sore, dan malam. Pada setiap kondisi tersebut memiliki tingkat kontras dan kecerahan yang bervariasi. Citra yang memiliki tingkat kontras yang cukup dan tinggi dapat dengan mudah dilakukan proses deteksi pelat nomor. Namun, pada kondisi citra yang memiliki tingkat kontras dan cahaya yang rendah tidak mudah untuk melakukan segmentasi karakter sehingga hasil deteksi pelat nomor menjadi tidak maksimal. Pada penelitian ini akan dibuat perbaikan kualitas citra untuk sistem LPR menggunakan Dynamic Histogram Equalization. Dynamic Histogram Equalization merupakan tahap praproses citra yang berfokus untuk meningkatkan segmentasi dan pengenalan karakter pada citra yang memiliki tingkat kontras dan kecerahan yang rendah. Selain itu, pada sistem juga ditambahkan metode yang dapat meningkatkan segmentasi dan pengenalan karakter seperti koreksi kemiringan pelat dan gamma correction. =================================================================================================== License Plate Recognition (LPR) technology has been adopted in many modern traffic applications, such as parking lots, traffic monitoring and road safety control. In the real world, the number plate recognition system is used in various conditions such as day, evening and night. In each of these conditions have varying levels of contrast and brightness. Images that have sufficient and high contrast levels can be easily detected by the number plate detection process. However, in image conditions that have low contrast and light, it is not easy to segment characters so that the number plate detection results are not optimal. In this final project, image quality improvement for the LPR system using Dynamic Histogram Equalization will be made. Dynamic Histogram Equalization is an image preprocessing stage that focuses on improving segmentation and character recognition in images with low contrast and brightness levels. In addition, the system also adds methods that can improve segmentation and character recognition, such as plate tilt correction and gamma correction. The tests were carried out in five scenarios, namely tilt correction testing, algorithm testing to improve image quality, gamma correction testing, character recognition testing and testing on video data comparing the system in previous studies with the system proposed in this final project. Optimal test results are obtained by using slope correction, preprocessing stage with xii Dynamic Histogram Equalization, Gamma Correction. In addition, the results of the introduction and a majority vote in this Final Project system are better than the system in previous studies with 97,4% recognition accuracy and 97,1% majority vote accuracy.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Koreksi Kemiringan, Dynamic Histogram Equalization, Gamma Correction, Skew Correction, Dynamic Histogram Equalization , Gamma Correction
Subjects: Q Science > Q Science (General) > Q325.5 Machine learning.
R Medicine > R Medicine (General) > R858 Deep Learning
T Technology > T Technology (General) > T57.83 Dynamic programming
T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques
Divisions: Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55201-(S1) Undergraduate Thesis
Depositing User: Safhira Maharani
Date Deposited: 29 Jul 2021 09:32
Last Modified: 29 Jul 2021 09:32
URI: https://repository.its.ac.id/id/eprint/84580

Actions (login required)

View Item View Item