Denis Andi Setiawan
Fakultas Ilmu Komputer, Universitas Brawijaya

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

Found 1 Documents
Search

Sistem Klasifikasi Jenis Karat Menggunakan Metode Decision Tree Berbasis Raspberry Pi Denis Andi Setiawan; Hurriyatul Fitriyah; Wijaya Kurniawan
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 2 (2019): Februari 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1084.332 KB)

Abstract

A place to collect is one of the management of an object that is no longer used or rusty. At the place of the clumping, the corroded object is sorted. However, rust detection is done manually through pieces with the naked eye. This method is vulnerable to human error. Based on these problems, it is necessary to have a system that can sort out the zinc automatically to facilitate the owner. In making this system, the image taken is zinc which has been corroded. This system takes the image of rust using a webcam. Rust from the image is detected using the thresholding method, then classified into mild rust or heavy rust which results will be displayed via LCD. The percentage limit of the rust classification will be determined by the decision tree method. Testing is done to find the percentage of system accuracy, and it can be concluded that the zinc painted in the rusty section has a percentage difference of 0.02 when compared to original rust, and original rust has class accuracy of 90% compared to the original class that has been determined by experts, and the execution time of this program is around 0.59.