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
Gagas Budi Waluyo
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 Kue Tradisional menggunakan Ekstraksi Fitur HSV Color Moment dan Local Binary Pattern dengan K-Nearest Neighbour Gagas Budi Waluyo; Yuita Arum Sari; Bayu Rahayudi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 12 (2021): Desember 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Traditional cakes or market snacks are traditional foods that we need to preserve, these traditional cakes are very rarely found today, because many people do not know about these traditional cakes and are very rarely found in this modern era. Actually this traditional cake is a delicious food and there are many various types and certainly not too many preservatives in it. But over time traditional cakes have been shifted by modern food and a lot of food is imported into the country, therefore it is time to preserve it so that it does not become extinct and posterity can find out. So a system is needed to recognize traditional cakes using technology as it is today n this study, to recognize traditional cakes using Hue Saturation Value (HSV) color feature extraction and Local Binary Pattern (LBP) texture features and classified using the K-Nearest Neighbor (KNN) method. The color feature used is the color moment which produces three values, namely the mean, standard deviation, and skewness. While the LBP texture feature will produce a grayscale value as much as the number of neighbors used. After that, the obtained feature extraction is classified using K-Nearest Neighbor. The test results show that if you only use the HSV color feature method, you get an accuracy value of 75%. If only using the LBP texture feature method, the accuracy value is 72.5%. Meanwhile, if the two feature extraction methods are combined, the accuracy value is 75%.
Co-Authors Bayu Rahayudi Yuita Arum Sari