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
Refi Fadholi
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 
Pengenalan Citra Makanan Tradisional menggunakan Fitur Hue Saturation Value dan Fuzzy k-Nearest Neighbor Refi Fadholi; Yuita Arum Sari; Fitra Abdurrachman Bachtiar
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 7 (2019): Juli 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (831.491 KB)

Abstract

Traditional food and snacks are typical of ancestors usually used for events or traditions. Some people consider that traditional food and snacks are obsolete, so that more traditional food and snacks are left behind by the people, and begin to shift to modern life, whereas traditional snacks themselves are one form of ancestral heritage that must preserved by next generation. Making system that can identify traditional types of food can be done using digital image processing. In this study, the image data used the result of image after segmentation with three types of data on testing, that is 300 images of the best segmentation result, 300 data of images with the amount of data each class is almost same and 400 data of images with the best segmentation results. Image feature used Hue Saturation Value (HSV) that contains mean, standard deviation, skewness and curtosis each color dimensions. Classification using the Fuzzy k-NN method and k-Fold Cross Validation. The test results based on values of k (k-Fold) and k (k-NN) obtained highest average accuracy at 53.33%. The test results also show that high color similarity between classes, poor image quality data and uneveness amount of data makes the test result decreased.
Co-Authors Fitra Abdurrachman Bachtiar Yuita Arum Sari