DEVELOPMENT OF A LONTARA CHARACTER DETECTION APPLICATION BASED ON CONVOLUTIONAL NEURAL NETWORKS USING THE FLUTTER FRAMEWORK
Main Article Content
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.
Article Details
References
[2] A. M. Ayyub HT and Indriani, “Revitalisasi Aksara Lontara sebagai Identitas Budaya bagi Siswa Suku Bugis Perantauan,” Nov. 2024. doi: https://doi.org/10.58230/27454312.1344.
[3] A. Kilawati, M. Zulham, and Sunardin, “PENGEMBANGAN BUKU BACA TULIS AKSARA LONTARA’ BERBASIS BUDAYA BUGIS UNTUK SEKOLAH DASAR,” no. Vol. 14 No. 2 (2023): Jurnal Pendidikan Dasar, Dec. 2023, doi: 10.21009/jpd.v14i2.
[4] Rismayanti, Apriyanto, and R. Suppa, “APLIKASI PEMBELAJARAN AKSARA LONTARA BUGIS BERBASIS ANDROID PADA SDN 152 CENNING DI DESA SALOBONGKO KECAMATAN MALANGKE BARAT,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 13, no. 2, Apr. 2025, doi: https://doi.org/10.23960/jitet.v13i2.6075.
[5] Agus Tri Haryanto, “Digitalisasi Aksara Lontara adalah Mimpi Lama yang Segera Terwujud,” Nov. 07, 2020. Accessed: Apr. 22, 2025. [Online]. Available: https://inet.detik.com/cyberlife/d-5245495/digitalisasi-aksara-lontara-adalah-mimpi-lama-yang-segera-terwujud
[6] M. Sabri, Nurhayati, and Syahrir, “Rancang Bangun Aplikasi Pembelajaran Aksara Lontara Bugis Makassar Berbasis Mobile,” Makassar, Oct. 2020.
[7] M. Mustafa, F. Wajidi, A. Amirul, A. Cirua, and N. Nur, “Pengenalan Huruf Aksara Lontara Menggunakan Metode Convolutional Neural Network,” Journal of Computer and Information System (J-CIS, vol. 7, no. 1, pp. 34–42, 2024, doi: 10.31605/jcis.v7i1.
[8] W. Arthanugraha, Z. Zainuddin, and A. L. Arda, “Implementation of Convolutional Neural Network in Recognize Lontara Text,” Jurnal Informatika, vol. 11, no. 2, pp. 65–72, Aug. 2024, doi: 10.31294/inf.v11i2.20328.
[9] R. Saneval Arhinza, A. Puspita Sari, and F. Ali Akbar, “Klasifikasi Citra Aksara Lontara menggunakan K-NN dan Ekstraksi Fitur HOG,” Sep. 2024. doi: http://dx.doi.org/10.29407/gj.v8i2.22580.
[10] A. Naufal Indisa, R. Dwiyansaputra, and F. Bimantoro, “IMPLEMENTASI MODEL MACHINE LEARNING PENGENALAN AKSARA BIMA MENGGUNAKAN APLIKASI PEMBELAJARAN AKSARA BIMA BERBASIS ANDROID (MACHINE LEARNING MODEL,” Jun. 2023.
[11] Abdul Rahim, Febryanti Sthevanie, and Kurniawan Nur Ramadhani, “Klasifikasi Aksara Lontara Dari Sulawesi Selatan Menggunakan CNN,” Jan. 2025, doi: http://dx.doi.org/10.25124/logic.v2i2.8812.
[12] N. P. I. P. Nurahdika and J. Sutopo, “ANALISA PERFORMA CONVOLUTION NEURAL NETWORK DALAM PENGENALAN TULISAN TANGAN AKSARA LONTARA PERFORMANCE ANALYSIS OF CONVOLUTIONAL NEURAL NETWORK IN HANDWRITTEN LONTARA SCRIPT RECOGNITION,” Journal of Information Technology and Computer Science (INTECOMS), vol. 8, no. 1, 2025.
[13] G. Samara, E. Al-Daoud, N. Swerki, and D. Alzu’bi, “The Recognition of Holy Qur’an Reciters Using the MFCCs’ Technique and Deep Learning,” Advances in Multimedia, vol. 2023, pp. 1–14, Mar. 2023, doi: 10.1155/2023/2642558.