Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Teknik Informatika (JUTIF)
Sakira, Tiara Putri
Unknown Affiliation
Computer Science & IT

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

Found 1 Documents
Search

 1 
MATURITY CLASSIFICATION SYSTEM OF TOMATO BASED ON RGB COLOR FEATURES USING BACKPROPAGATION ARTIFICIAL NEURAL NETWORK METHOD Massie, Gary Jeremi; Pratama, Azir Zuldani; Sakira, Tiara Putri; Kaswar, Andi Baso; Andayani, Dyah Darma
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 1 (2024): JUTIF Volume 5, Number 1, February 2024
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.1.732

Abstract

Determining the ripeness level of tomatoes, for now, is still done manually (conventional), and in general, determining the ripeness of tomatoes using the manual method often gets inconsistent results due to differences in everyone's perception so in determining ripe or not ripe tomatoes to be not very accurate. There have been various previous studies that have been conducted, especially in terms of classifying maturity levels, but from these studies, the level of accuracy achieved is relatively low. Therefore, the researcher proposes research on Tomato Fruit Maturity Classification System Based on RGB Color Features Using the Backpropagation Neural Network Method. This research consists of the image acquisition stage, the preprocessing stage, the image segmentation stage including performing morphological operations, the RGB feature extraction stage, and the last stage is conducting Image Classification using Backpropagation Neural Networks. From the results of the training phase, the resulting computational time is 87,735 seconds with an overall accuracy rate of 99.04%. And based on the results of the testing phase, the architecture of the backpropagation neural network that has been built can accurately classify the ripeness level of tomatoes, from a total of 90 test images, with an accuracy of 98.88% obtained and a more efficient computational time of 30.390 seconds. This can help farmers in harvesting tomatoes.
Co-Authors Andi Baso Kaswar Andi Baso Kaswar Massie, Gary Jeremi Pratama, Azir Zuldani