Pengenalan dan Alih Aksara Jawa Pada Citra Menggunakan YOLOv11
Abstract
Abstrak — Aksara Jawa sebagai salah satu warisan budaya Indonesia menghadapi ancaman kepunahan akibat rendahnya tingkat literasi serta dominasi alfabet Latin dalam kehidupan modern. Kompleksitas bentuk visual aksara, disertai kemiripan karakter antaraksara, turut menyulitkan proses identifikasi secara manual. Penelitian ini mengembangkan sistem deteksi dan alih aksara Jawa otomatis berbasis teknologi deep learning. Sistem dibangun menggunakan dua varian model YOLOv11, yaitu YOLOv11n dan YOLOv11x, dengan memanfaatkan dataset gabungan yang terdiri atas data primer sebanyak 49 kelas dan data sekunder sebanyak 20 kelas aksara dasar. Dataset melalui tahap preprocessing dan augmentasi data berupa blur dan noise sebelum dilakukan pelatihan model selama 100 epoch dengan konfigurasi optimal. Evaluasi kinerja model dilakukan menggunakan metrik precision, recall, F1-Score, dan mAP50. Hasil pengujian menunjukkan bahwa YOLOv11n memperoleh nilai precision 0,9473, recall 0,9847, F1-Score 0,9656, dan mAP50 0,9818, sedangkan YOLOv11x mencapai precision 0,9850, recall 0,9925, F1-Score 0,9887, dan mAP50 0,9944. Kedua model mampu mendeteksi aksara dasar, pasangan, dan sandhangan secara akurat serta mendukung proses alih aksara ke huruf Latin, sehingga berpotensi menjadi solusi berbasis teknologi dalam upaya pelestarian aksara Jawa melalui pengolahan citra.
Kata kunci — alih aksara, deep learning, pengenalan aksara Jawa, pelestarian budaya, pengolahan citra, YOLOv11.
References
REFERENSI
M. Matsuri et al., “Analysis of Elementary School Students’ Literacy Ability of Javanese Script Through the Use of Script Card Reviewed Based on Critical Thinking Skills,” AIJP, vol. 15, no. 4, Dec. 2023, doi: 10.35445/alishlah.v15i4.4519.
S. A. Ori and H. W. Susianti, “Preserving Javanese Language and Culture in The Digital Age : Challenge and Future Prospects,” lacultour, vol. 2, no. 2, pp. 79–88, Nov. 2023, doi: 10.52352/lacultour.v2i2.1212.
H. O. Fajrin, “THE INFLUENCE OF TECHNOLOGY-BASED MEDIA OF DIGITAL JAVANESE SCRIPT AMONG JUNIOR HIGH SCHOOL STUDENTS,” Jurnal Ilmiah WUNY, vol. 5, no. 1, May 2023, doi: 10.21831/jwuny.v5i1.58374.
D. Iskandar, S. Hidayat, U. Jamaludin, and S. Mukti Leksono, “Javanese script digitalization and its utilization as learning media: an etnopedagogical approach,” J.IJMSEd, vol. 1, no. 1, pp. 21–30, June 2023, doi: 10.59965/ijmsed.v1i1.24.
A. A. Rahmawati, A. Muhaimin, and D. A. Prasetya, “CLASSIFICATION OF JAVANESE NGLEGENA SCRIPT USING COMPLEXVALUED NEURAL NETWORK,” jiko, vol. 7, no. 1, pp. 30–35, Apr. 2024, doi: 10.33387/jiko.v7i1.7808.
M. A. Rasyidi, T. Bariyah, Y. I. Riskajaya, and A. D. Septyani, “Classification of handwritten Javanese script using random forest algorithm,” Bulletin EEI, vol. 10, no. 3, pp. 1308–1315, June 2021, doi: 10.11591/eei.v10i3.3036.
A. Susanto, I. U. W. Mulyono, C. A. Sari, E. H. Rachmawanto, D. R. I. M. Setiadi, and M. K. Sarker, “Improved Javanese script recognition using custom model of convolution neural network,” IJECE, vol. 13, no. 6, p. 6629, Dec. 2023, doi: 10.11591/ijece.v13i6.pp6629-6636.
R. Rosalina, N. Afriliana, W. H. Utomo, and G. Sahuri, “Deep learning utilization in Sundanese script recognition for cultural preservation,” IJEECS, vol. 36, no. 3, p. 1759, Dec. 2024, doi: 10.11591/ijeecs.v36.i3.pp1759-1768.
R. Sapkota, Z. Meng, M. Churuvija, X. Du, Z. Ma, and M. Karkee, “Comprehensive Performance Evaluation of YOLOv12, YOLO11, YOLOv10, YOLOv9 and YOLOv8 on Detecting and Counting Fruitlet in Complex Orchard Environments,” Feb. 25, 2025, arXiv: arXiv:2407.12040. doi: 10.48550/arXiv.2407.12040.
T. Saidani, “Efficient Tumor Detection in Medical Imaging Using Advanced Object Detection Model: A Deep Learning Approach,” ijacsa, vol. 16, no. 1, 2025, doi: 10.14569/ijacsa.2025.01601109.
N. Nabilah and F. Nikmah, “The RELATIONSHIP OF AKSARA JAWA AS LOCAL FOLKLORE WITH MODERATE AND PROGRESSIVE ISLAMIC EDUCATION,” AICOIES, vol. 1, no. 1, June 2022, doi: 10.18326/aicoies.v1i1.257.
H. A. Ikasanti, N. K. Umam, and I. Marzuki, “PENGEMBANGAN VIDEO PEMBELAJARAN UNTUK MEMBACA AKSARA JAWA PADA PESERTA DIDIK KELAS IV SEKOLAH DASAR,” jtiee, vol. 5, no. 1, p. 1, May 2021, doi: 10.30587/jtiee.v5i1.2786.
H. A. Nugroho, D. Sulaksono, and R. Rahmat, “Analisis Kesalahan Penulisan Aksara Jawa Pada Papan Nama Jalan di Kota Surakarta,” sabpbj, vol. 7, no. 1, p. 26, Mar. 2023, doi: 10.20961/sabpbj.v7i1.61367.
R. R. Karim, “IMPLEMENTASI KLASIFIKASI SENJATA TRADISIONAL JAWA BARAT MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK (CNN) DENGAN METODE TRANSFER LEARNING,” JITET, vol. 12, no. 2, Apr. 2024, doi: 10.23960/jitet.v12i2.4166.
A. T. Akbar, S. Saifullah, and H. Prapcoyo, “Klasifikasi Ekspresi Wajah Menggunakan Covolutional Neural Network,” JTIIK, vol. 11, no. 6, pp. 1399–1412, Dec. 2024, doi: 10.25126/jtiik.1168888.
Y. N. Fuadah, I. D. Ubaidullah, N. Ibrahim, F. F. Taliningsing, N. K. Sy, and M. A. Pramuditho, “Optimasi Convolutional Neural Network dan K-Fold Cross Validation pada Sistem Klasifikasi Glaukoma,” ELKOMIKA, vol. 10, no. 3, p. 728, July 2022, doi: 10.26760/elkomika.v10i3.728.
R. Sapkota et al., “YOLOv12 to Its Genesis: A Decadal and Comprehensive Review of The You Only Look Once (YOLO) Series,” Feb. 21, 2025, arXiv: arXiv:2406.19407. doi: 10.48550/arXiv.2406.19407.
Y. Luo, “The Evolution of YOLO: from YOLOv1 to YOLOv11 with a Focus on YOLOv7’s Innovations in Object Detection,” TNS, vol. 87, no. 1, pp. 82–90, Jan. 2025, doi: 10.54254/2753-8818/2025.20335.
R. Sapkota and M. Karkee, “Improved YOLOv12 with LLM-Generated Synthetic Data for Enhanced Apple Detection and Benchmarking Against YOLOv11 and YOLOv10,” Mar. 19, 2025, arXiv: arXiv:2503.00057. doi: 10.48550/arXiv.2503.00057.
R. Sapkota and M. Karkee, “Comparing YOLOv11 and YOLOv8 for instance segmentation of occluded and non-occluded immature green fruits in complex orchard environment,” Jan. 26, 2025, arXiv: arXiv:2410.19869. doi: 10.48550/arXiv.2410.19869.
R. Sapkota, Z. Meng, M. Churuvija, X. Du, Z. Ma, and M. Karkee, “Comprehensive Performance Evaluation of YOLOv12, YOLO11, YOLOv10, YOLOv9 and YOLOv8 on Detecting and Counting Fruitlet in Complex Orchard Environments,” Feb. 25, 2025, arXiv: arXiv:2407.12040. doi: 10.48550/arXiv.2407.12040.
