Fachruddin, Rifqi (2022) Sistem Deteksi Lingkaran Berbasis Image Moments. Masters thesis, Institut Teknologi Sepuluh Nopember.
|
Text
05111950015003-Master_Thesis.pdf Restricted to Repository staff only Download (3MB) |
Abstract
Sistem deteksi lingkaran mengalami perkembangan yang signifikan. Sistem deteksi lingkaran digunakan untuk membantu manusia berdasarkan kebutuhan atau kegiatan tertentu, salah satunya sebagai media pembelajaran dalam bidang Pendidikan. Sistem deteksi lingkaran pada media Augmented Reality (AR) akan sangat membantu sebagai media belajar. Dengan memerhatikan tujuan untuk membuat proses belajar efektif dan sesuai dengan materi pembelajaran, sistem deteksi lingkaran yang dibutuhkan adalah sistem yang mampu mendeteksi hanya perfect circle, untuk meminimalisir miskonsepsi pada materi lingkaran. Berdasarkan metode sebelumnya, yaitu Circular Hough Transform (CHT), sistem deteksi lingkaran menghadapai kesulitan dalam mengonversi koordinat kartesius ke koordinat parameter. Penggunaan image moments dalam sistem deteksi lingkaran akan memermudah menemukan informasi koordinat pusat lingkaran dan dapat digunakan untuk menemukan jari-jari lingkaran menggunakan persamaan lingkaran. Dataset yang digunakan dalam penelitian ini terdiri atas tiga, dataset pertama adalah 30 gambar lingkaran perfect circle dan lingkaran dengan sudut pandang berbeda-beda sehingga terlihat seperti ellips. Dataset kedua adalah 32 gambar riil yang diantaranya terdapat 18 gambar dengan tingkat noise yang berbeda-beda. Dataset ketiga adalah 10 gambar hasil tangkapan kamera smartphone. Berdasarkan hasil eksperimen, rata-rata persentase akurasi sistem deteksi lingkaran berbasis image moments adalah sebesar 81,91%, sedangkan akurasi sistem deteksi lingkaran menggunakan CHT sebesar 61,38%. Kemudian time consumption, secara umum sistem deteksi lingkaran berbasis image moments lebih cepat daripada sistem deteksi lingkaran menggunakan CHT. Sedangkan untuk pengaruh noise terhadap sistem deteksi adalah sistem deteksi lingkaran berbasis image moments memiliki ketahanan yang sama dengan sistem deteksi lingkaran menggunakan CHT.
==============================================================================================================================
The growth of system detection has significant development. The circle detection system is widely used to help people based on their needs, and it also could be used as learning media in educational fields. Especially for students with special needs, applying a circle detection system in Augmented Reality (AR) media would help them a lot. In order to make the study activity more effective and suit the learning material purpose, a circle detection system that only detects perfect full circles is needed to minimalize misconceptions in circle learning material. From the previous method such as Circle Hough Transform (CHT), circle detection faces the complex transition from cartesian coordinate into Hough coordinate. The use of image moments would give a coordinate of centroid that could use to find the radius by using the circle equation. Three groups of datasets would test the newly proposed method of detecting circles. The first dataset was 30 digital image generated by Python, the second dataset was 32 real image with kind of noises percentage, and the third dataset was 10 real image captured from smartphone camera. Based on the experiment, the average accuracy of circle detection system using image moments was 81.91% and circle detection system using CHT was 61.38%. The average time consumption of circle detection system using image moments is faster than CHT method. Circle detection system using image moments is as same robust towards noise as circle detection system using CHT.
| Item Type: | Thesis (Masters) |
|---|---|
| Additional Information: | RSIf 006.42 Fac s-1 2022 |
| Uncontrolled Keywords: | Sistem deteksi lingkaran, image moments, circular hough transform. circle detection, image moments, circle hough transform. |
| Subjects: | T Technology > T Technology (General) > T58.5 Information technology. IT--Auditing |
| Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55101-(S2) Master Thesis |
| Depositing User: | Mr. Marsudiyana - |
| Date Deposited: | 09 Jul 2026 06:41 |
| Last Modified: | 09 Jul 2026 06:41 |
| URI: | http://repository.its.ac.id/id/eprint/134591 |
Actions (login required)
![]() |
View Item |
