Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Kharisma Tech
Linda Yanti Yo
Unknown Affiliation
Computer Science & IT Engineering

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

Found 1 Documents
Search
Journal : kharisma tech

 1 
DEVELOPMENT OF A LONTARA CHARACTER DETECTION APPLICATION BASED ON CONVOLUTIONAL NEURAL NETWORKS USING THE FLUTTER FRAMEWORK Linda Yanti Yo; Mohammad Fajar; Baizul Zaman
KHARISMA Tech Vol 21 No 2 (2026): KHARISMATech Journal
Publisher : STMIK KHARISMA Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55645/kharismatech.v21i2.603

Abstract

Lontara script is a cultural heritage of the Bugis-Makassar people that is increasingly threatened with extinction due to the limited availability of interactive learning media. This study aims to develop a mobile application for detecting Lontara script based on Flutter, integrated with a Convolutional Neural Network (CNN) model. The dataset consists of 5,017 images of Lontara script divided into 23 classes, processed through grayscale and normalization stages. The CNN model is designed with three layers of convolution and pooling, then evaluated using accuracy, precision, recall, and F1-score metrics. Testing results show that the application can detect Lontara script in real-time through Flutter and REST API integration, with the model achieving 97% accuracy. Testing under conditions with visual disturbances showed that the model could still perform detection up to a certain level of noise and blur, but performance declined under high simultaneous disturbances. These findings confirm that the application can support efforts to preserve Lontara script, though it still requires adequate image quality for optimal detection.
Co-Authors Mohammad Fajar, Mohammad