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
Rr Dea Annisayanti Putri
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 
Pemanfaatan Metode Texture-Based Region Growing Untuk Segmentasi Buah Jeruk Keprok (Citrus Reticulata Blanco) Rr Dea Annisayanti Putri; Agus Wahyu Widodo; Muhammad Arif Rahman
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 4 (2019): April 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (863.403 KB)

Abstract

Indonesia is a producer of “Keprok” and the largest harvest area in ASEAN. In market competition, the most important thing for oranges is quality. The visual technology method can be used to replace the quality determination process that is still manual. One process of determining automatic quality is segmentation. Segmentation is the process of separating objects studied from less important parts. The segmentation process is an important process in determining quality, the results of segmentation must be precise, no under segmentation or no over segmentation. This study uses the region growing method with texture value parameters obtained from contrast, homogeneity, entropy, and energy features in the gray level co-occurrence matrix (GLCM) method. First, the image of oranges is taken. In the image of oranges, pre-processing takes the form of changing the color and size of the image. Then the image of the orange is divided into a collection of pixels called windows, with sizes 10, 20, 50, and 100 pixels. From the window group, one window will be selected which becomes the starting point for region growing. In the initial window and 8 neighbor windows, feature values are taken. The neighboring window is considered to be the orange part if it has a feature value according to the boundary. This study resulted in the best level of segmentation accuracy of 84.7% with a window size of 50x50 pixels, an entropy feature, and a limit value of 5.
Co-Authors Agus Wahyu Widodo Muh. Arif Rahman