Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Fajri Eka Saputra
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

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

Found 1 Documents
Search

 1 
Penentuan Kualitas Biji Kopi Menggunakan Local Ternary Patterns Dan RGB-HSV Color Moment Dengan Learning Vector Quantization Fajri Eka Saputra; Randy Cahya Wihandika; Agus Wahyu Widodo
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 6 (2021): Juni 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Coffee cultivation in Indonesia is still done by very traditional methods, like wise in determination of its quality level by sorting it out still done by human operators by considering its size and density, which means determination of coffee bean's quality level is very depended on the operator's ability, so that is susceptible to mistakes and non-technical factors that accompany it. The quality level of coffee bean itself is divided to 6 grades that is grade 1 to grade 6 for each variant. One of the methods that can be done to ease determination of the quality of coffee beans is by processing its image by extracting texture feature by using Local Ternary Patterns(LTP) method, color feature with HSV and RGB Color Moment, and utilizing classification algorithm Learning Vector Quantization (LVQ). This method is considered as a breakthrough in coffee bean's grade determination because the cost is cheaper but still gives decent results considered in a relatively short time. In this study, the image data used is as many as 150 data with 30 data on grade 1 through 5 because the data availability was not up to grade 6. This study results a system that was able to classify the quality of coffee beans with an accuracy rate of 84,4%. Two of the entered quality cases were successfully predicted with 100% correctness, namely grade 1 and 5.
Co-Authors Agus Wahyu Widodo Randy Cahya Wihandika