Mohammad Rizky Hidayatullah
Fakultas Ilmu Komputer, Universitas Brawijaya

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

Found 1 Documents
Search

Algoritme Enhanced K-Means dengan Ekstraksi Fitur Local Binary Pattern dan Color Moment untuk Pengelompokan Citra Makanan Mohammad Rizky Hidayatullah; Yuita Arum Sari; Randy Cahya Wihandika
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 (402.709 KB)

Abstract

Food is a source of our energy for doing our daily activities. Food have each color and texture for their identity. Using color and texture from the food, we can feel the taste in our mind while we see that food. In this paper, we want to know about what information we can get with color and texture of food. To do that, we use clustering to see how color and texture can show any information like nutrition inside the food. We used Enhanced K-means for grouping food image because we want to get a consistent results cause in Enhanced K-means, the initialization didn't use random data. The food image is grouping by color and texture cause they are two thing who can increase someones appetite. To get the color feature we used Color Moment and for texture feature we used Local Binary Pattern. For the result of evaluation using Coefficient Silhouette (CS) and Davies-Boulding Index (DBI), clustering using color texture get best result with DBI score is 0.957 and Silhouette score is 0.399 whereas when we use color and texture, result for DBI score is just 1.058 and Silhouette score is 0.31.