Pengenalan Nomor Polisi Kendaraan pada Data Video Menggunakan Convolutional Neural Network

Baskara, Pradipta (2019) Pengenalan Nomor Polisi Kendaraan pada Data Video Menggunakan Convolutional Neural Network. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 05111540000055-Undergraduate_Theses.pdf - Accepted Version Restricted to Repository staff only Download (1MB) | Request a copy

Abstract

Machine learning telah menjadi bagian dari kehidupan sehari-hari bagi banyak orang. Salah satu pengaplikasian machine learning adalah pengenalan nomor polisi kendaraan. Pengenalan nomor polisi kendaraan mengkategorikan citra karakter-karakter yang ada. Banyak perusahaan, badan riset dan universitas yang terus mengembangkan machine learning agar mendapat hasil yang lebih akurat dan cepat. Dari situlah lahir algoritma deep learning, yang merupakan bagian dari machine learning. Convolutional Neural Network (CNN) adalah salah satu deep neural network yang cocok digunakan untuk mengolah data yang berbentuk 2 dimensi, seperti gambar dan video. Pada tugas akhir ini, penulis mengusulkan penggunaan CNN untuk melakukan pengenalan karakter plat nomor pada data video. Tujuannya adalah untuk membangun sistem yang dapat mengenali karakter pada citra plat nomor. Data pelatihan dan uji merupakan data yang diambil secara mandiri oleh penulis. Data latih merupakan karakter-karakter dari citra plat nomor yang telah dilakukan proses cropping. Praproses terhadap data antara lain dilakukan perubahan kanal citra menjadi grayscale, padding, perubahan resolusi gambar menjadi 32x32 piksel, dilakukan proses morfologi, dan dilakukan proses augmentasi data berupa rotasi dan perbesaran ukuran gambar. Hasil uji coba optimal didapatkan dari arsitektur CNN dengan optimizer Adam, ukuran kernel 4x4 pada Convolution Layer ketiga, dan lokalisasi YOLO dengan nilai akurasi 89,53%
====================================================================================================================================
Machine learning has become a part of the daily life of people around the world. One of the application of machine learning is automatic plate number recognition. Automatic plate number recognition categorize characters found on the plate itself. Many companies, researchers and universities keep improving the machine learning to get a better and faster result. And from those improvements, deep learning algorithm is born. Convolutional Neural Network (CNN) is one of the deep neural network that suitable to process 2 dimentional data like image and video. In this undergraduate thesis, author suggest the use of CNN to classify characters from the plate number. The purpose of this undergraduate thesis is to build a system that can regognize characters on plate number. The datasets itself are taken by the author from author’s surrounding neighborhood vehicles while the data test also taken by the author surrounding neighborhood vehicles. The data train are characters, cropped from plate number that taken by the author. Some preprocessing include are image grayscaling, image padding, resizing to 32x32 size, morphological operation, and data augmentation to increase the variety of the dataset. Final optimal result got from the testing from CNN architecture with Adam optimizer, kernel size 4x4 on the third Convolution Layer and YOLO localization are 89,53% for testing accuracy.

Item Type:	Thesis (Other)
Additional Information:	RSIf 006.31 Bas p-1 2019 3100019082731
Uncontrolled Keywords:	Convolutional Neural Network, Data Citra, Pengenalan nomor polisi kendaraan
Subjects:	Q Science > QA Mathematics > QA336 Artificial Intelligence Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques. Image analysis--Data processing.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55201-(S1) Undergraduate Thesis
Depositing User:	Pradipta Baskara
Date Deposited:	10 Dec 2025 08:25
Last Modified:	10 Dec 2025 08:25
URI:	http://repository.its.ac.id/id/eprint/68146

Actions (login required)

View Item