Article Per Year (5 Year)
p-Index From 2020 - 2025
0
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Fida Dwi Febriani
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 
Klasifikasi Citra Kue Tradisional Indonesia Berdasarkan Ekstraksi Fitur Warna RGB Color Moment Menggunakan K-Nearest Neighbor Fida Dwi Febriani; Yuita Arum Sari; Randy Cahya Wihandika
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 10 (2019): Oktober 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (275.03 KB)

Abstract

Food is one of the needs in primary needs which is very important for humans. These needs must be met every day, but the human tendency for food needs changes with the times. Society in general will choose fast food that is ready to be served rather than choosing traditional food. In this day and age, most people tend to capture the moment when they want to enjoy a food that will be consumed. Taking pictures (photos) is one way, from which the images are obtained an image on food. The image will display several different colors, so the color will be a feature that can be used for extraction. One method used to extract color features in images is Color Moment. This feature will produce three main values namely mean, standard deviation, and skewness. In addition, this feature together with the K-Nearest Neighbor (K-NN) algorithm will classify the extracted colors based on training data taken as many as k values. In this study, there are 29 Indonesian traditional cake objects that will be used, where the test scenario is divided into 29 classes, 8 classes, 5 classes, and 3 classes. By using the K-NN method and the Color Moment feature, the highest evaluation value obtained is 60% for the test scenario of 3 classes.
Co-Authors Randy Cahya Wihandika Yuita Arum Sari