KLASIFIKASI RAMBU LALU LINTAS MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK

HISBULLAH, MUHAMMAD AZKA and Fachrurrozi, Muhammad and Rachmatullah, Muhammad Naufal (2023) KLASIFIKASI RAMBU LALU LINTAS MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021281924071.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_55201_09021281924071_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_55201_09021281924071_0222058001_0001129204_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (2MB)
	Text RAMA_55201_09021281924071_0222058001_0001129204_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (377kB) | Request a copy
	Text RAMA_55201_09021281924071_0222058001_0001129204_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (432kB) | Request a copy
	Text RAMA_55201_09021281924071_0222058001_0001129204_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (619kB) | Request a copy
	Text RAMA_55201_09021281924071_0222058001_0001129204_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (816kB) | Request a copy
	Text RAMA_55201_09021281924071_0222058001_0001129204_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (57kB) | Request a copy
	Text RAMA_55201_09021281924071_0222058001_0001129204_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (130kB) | Request a copy
	Text RAMA_55201_09021281924071_0222058001_0001129204_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (88kB) | Request a copy

Abstract

Classification of traffic signs is considered as one of the most important parts of the Advance Driver Assistance System (ADAS) with the main objective of reducing the number of road accidents and overcoming wrong route selection. Convolutional Neural Network (CNN) is a type of neural network that is commonly used in image data. CNN can be used to recognize and detect objects in an image. Image enhancement has an important role in improving image quality in the field of image processing, which is achieved by highlighting useful information and suppressing redundant information in images. This study uses the German Traffic Sign Recognition Benchmark dataset which contains 51,840 images of traffic signs in Germany with 43 classes. The evaluation results of the Xception architecture using Gaussian-blur with a batch size of 32 and a learning rate of 0.0001 produce a training data accuracy value of 99.99% with a test data accuracy of 98.63%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Klasifikasi Rambu Lalu Lintas, Convolutional Neural Network, German Traffic Sign Recognition Benchmark
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General) T Technology > T Technology (General) > T1-995 Technology (General) > T9 General works
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Muhammad Azka Hisbullah
Date Deposited:	31 Aug 2023 05:58
Last Modified:	31 Aug 2023 05:58
URI:	http://repository.unsri.ac.id/id/eprint/128079

Actions (login required)

View Item