Rizky Teguh Nursetyawan
Fakultas Ilmu Komputer, Universitas Brawijaya

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Pengembangan Sistem Rekognisi Rambu Kecepatan Menggunakan Circle Hough Transform dan Convolutional Neural Network Rizky Teguh Nursetyawan; Fitri Utaminingrum
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 11 (2020): November 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Motor vehichle is a kind of transportation mode that are popular among people in Indonesia. Annually the increase in number of drivers is growing rapidly. Safety always comes first in driving for the sake of avoiding accidents. Accidents occur because of many driver's negligence factors such as drowsy when driving, bad facilities and infrastructure, using device that takes away your attention from the road and ignorant of the speed limit sign. For sake of helping the drivers to manage their speed according to the sign, it is needed of a system that can help remind the driver of the existence of the sign. Before fulfilling the task of reminding the drivers surely the system would need to be able to detect and recognize the speed sign. In this research the writer would want to propose the usage of Circle Hough Transform as the method of detection dan Convolutional Neural Network as the method of recognition with the purpose of knowing the performance of both method in doing their task. Both of the methods are in the field of study of Digital Image Processing and Machine Learning respectively that is well-known with its big computational need. The big computational need is the reason minicomputer raspberry pi is chosen as the base processing unit of the system compared to microcontroller. The result of testing for detection and recognition on Day 80% and night 70% . Looking from the results the methods that are proposed are not great but the writer believe that for the future research there is still room for improvement of the Circle Hough Transform and Convolutional Neural Network