Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal RABIT: Jurnal Teknologi dan Sistem Informasi Univrab
Melita Saldila
universitas Malikussaleh
Computer Science & IT Engineering

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

Found 1 Documents
Search

 1 
IMPLEMENTASI AUGMENTED REALITY UNTUK PENGENALAN TANAMAN TOGA MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK Melita Saldila; Rozzi Kesuma Dinata; Said Fadlan Anshari
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 1 (2026): Januari
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i1.6602

Abstract

This research aims to develop an Augmented Reality (AR) based application integrated with Convolutional Neural Network (CNN) method to help communities recognize Family Medicinal Plants (TOGA) interactively and increase awareness of their potential benefits. The developed application uses AR technology to provide direct information about TOGA plants detected through mobile phone cameras, with a dataset covering 10 types of TOGA plants, each containing 200 images per label. The research results show that the system successfully performs plant recognition in real-time with an accuracy rate of 58.53%, precision of 58.76%, and recall of 99.40%. The CNN model is capable of recognizing various visual variations of plants under different lighting conditions and viewing angles. Model training was conducted up to 125,000 steps with the best performance achieved at the 72,000th checkpoint. Although the application can provide an engaging and effective learning experience, the main challenge faced is the diversity of physical forms of plants within each category that affects system accuracy. This research proves that the combination of AR and CNN technologies can be used as an innovative solution for medicinal plant education, although further development is still needed to improve recognition accuracy.
Co-Authors Rozzi Kesuma Dinata Said Fadlan Anshari