Implementasi Convolutional Neural Network Untuk Pengenalan Tulisan Tangan Akasara Sunda Ngalangéna
-
Rahma Nur Azizah
*
Universitas Teknologi Yogyakarta, Yogyakarta,
Indonesia
https://orcid.org/0009-0005-8424-8058
- Donny Avianto Universitas Teknologi Yogyakarta, Yogyakarta, Indonesia https://orcid.org/0000-0001-5499-5478 (*) Corresponding Author
Abstract
Efforts to preserve the Sundanese script as a cultural heritage face challenges in the digital era, one of which is the limited resources for pattern recognition. This research aims to develop an effective custom Convolutional Neural Network (CNN) model for the classification of handwritten Sundanese script. Facing the constraint of no available public dataset, this study utilizes a primary dataset (Swaraksara Dataset) created by the author, consisting of 6,500 handwritten images evenly distributed across 13 classes (combinations of the "Na" script with rarangkén). The methodology applied includes a comprehensive data preprocessing stage, covering grayscale conversion, resizing to 200x200 pixels, normalization, and data augmentation techniques to prevent overfitting. The custom CNN architecture was designed with five convolutional layers (filters 32 to 512) and the Adam optimizer. The experimental results show that the optimal configuration was achieved with a learning rate of 0.001 and 50 training epochs, resulting in very high model performance. In the evaluation using test data, the model achieved an accuracy of 99.54% with a loss value of 0.0175. The optimal performance of this model is driven by the quality of the primary dataset supported by comprehensive image preprocessing stages, thus ensuring clean, uniform, and significantly noise-free data input. Analysis of the confusion matrix and learning curves also confirmed the model's excellent generalization ability with no indications of overfitting. This model has been successfully implemented in the "Swaraksara" web application as a Sundanese script recognition system.
Downloads
References
Abdiansah, L., Sumarno, S., Eviyanti, A., & Azizah, N. L. (2025). Penerapan Algoritma Convolutional Neural Networks untuk Pengenalan Tulisan Tangan Aksara Jawa. MALCOM: Indonesian Journal of Machine Learning and Computer Science, 5(2), 496–504. https://doi.org/10.57152/malcom.v5i2.1814
Adella, V. G., Rusbandi, & Devella, S. (2023). Pengenalan Tulisan Tangan Bahasa Korea Menggunakan Convolutional Neural Network Arsitektur ALEXNET. JIKI (Jurnal Ilmu Komputer dan Informatika), 4(1), 1–7. https://doi.org/https://doi.org/10.24127/jiki.v4i1.3311
Arief, N. S., Putra, W. A., Septhian, D., & Pratama, R. (2024). Implementasi Cnn Arsitektur Mobilenetv2 Untuk Klasifikasi Tulisan Aksara Jawa (Vol. 3). https://doi.org/https://doi.org/10.29407/z1cbjw36
Aryanto, R., Alfan Rosid, M., & Busono, S. (2023). Penerapan Deep Learning untuk Pengenalan Tulisan Tangan Bahasa Aksara Lota Ende dengan Menggunakan Metode Convolutional Neural Networks. Jurnal Informasi dan Teknologi, 5(1), 258–264. https://doi.org/10.37034/jidt.v5i1.313
Hadhiwibowo, A., Asri, S. R., & Dinata, R. A. (2024). Penerapan Convolutional Neural Network dengan Arsitektur Mobilenetv2 Pada Aplikasi Penerjemah dan Pembelajaran Bahasa Isyarat. TIN: Terapan Informatika Nusantara, 4(8), 518–523. https://doi.org/10.47065/tin.v4i8.4879
Khumaidi, A., & Nurpadilah, A. (2024). Klasifikasi Molting Kepiting Soka Menggunakan Algoritma Convolusional Neural Network. KOMPUTA: Jurnal Ilmiah Komputer dan Informatika, 13(2), 43. https://doi.org/https://doi.org/10.34010/komputa.v13i2.13984
Nur Azizah, A., Falach Asy’ari, M., Wisma Dwi Prastya, I., & Purwitasari, D. (2023). Easy Data Augmentation untuk Data yang Imbalance pada Konsultasi Kesehatan Daring. Jurnal Teknologi Informasi dan Ilmu Komputer, 10(5), 1095–1104. https://doi.org/10.25126/jtiik.2023107082
Nurhidayat, R., & Dewi, K. E. (2023). Penerapan Algoritma K-Nearest Neighbor Dan Fitur Ekstraksi N-Gram Dalam Analisis Sentimen Berbasis Aspek. 12(1), 91–100. https://doi.org/https://doi.org/10.34010/komputa.v12i1.9458
Putra, F., Tahiyat, H. F., Ihsan, R. M., Rahmaddeni, R., & Efrizoni, L. (2024). Penerapan Algoritma K-Nearest Neighbor Menggunakan Wrapper Sebagai Preprocessing untuk Penentuan Keterangan Berat Badan Manusia. MALCOM: Indonesian Journal of Machine Learning and Computer Science, 4(1), 273–281. https://doi.org/10.57152/malcom.v4i1.1085
Putri, C. N., Qornain, W. D., Bamahri, F., Yuliastuti, G. E., & Kurniawan, M. (2024). Klasifikasi Jenis Jerawat pada Data Citra Jerawat Wajah Menggunakan Convolutional Neural Network. TIN: Terapan Informatika Nusantara, 5(2), 172–181. https://doi.org/10.47065/tin.v5i2.5231
Rahmawati, S. N., Hidayat, E. W., & Mubarok, H. (2021). Implementasi Deep Learning Pada Pengenalan Aksara Sunda Menggunakan Metode Convolutional Neural Network. INSERT: Information System and Emerging Technology Journal, 2(1), 46. https://doi.org/https://doi.org/10.23887/insert.v2i1.37405
Rewina, A. E., Sulistyowati, S., Kurniawan, M., N, M. D., & Yunanda, S. F. (2024). Penerapan Metode CNN (Convolutional Neural Network) dalam Mengklasifikasi Uang Kertas dan Uang Logam. TIN: Terapan Informatika Nusantara, 4(12), 778–785. https://doi.org/10.47065/tin.v4i12.5128
Rodiah, Susetianingtias, D. T., & Patriya, E. (2025). Model Convolutional Neural Network (CNN) Custom Sequential untuk Klasifikasi Citra Ikan Hias Carassius Auratus pada Industri Akuakultur. Decode: Jurnal Pendidikan Teknologi Informasi, 5(3), 813–825. https://doi.org/10.51454/decode.v5i3.1229
Rosalina, Afriliana, N., Utomo, W. H., & Sahuri, G. (2024). Deep learning utilization in Sundanese script recognition for cultural preservation. Indonesian Journal of Electrical Engineering and Computer Science, 36(3), 1759–1768. https://doi.org/10.11591/ijeecs.v36.i3.pp1759-1768
Septian Nugraha, M., Dewi Ariessanti, H., & Akbar, H. (2025). Komparasi Model CNN untuk Klasifikasi Citra Pakaian Adat Tradisional Indonesia. JIM: Jurnal Ilmu Multidisplin, 4(4), 2404–2416. https://doi.org/https://doi.org/10.38035/jim.v4i4.1245
Swasono, N. E., Himamunanto, A. R., & Budiati, H. (2024). Pengenalan Karakter Huruf Pada Gambar Tulisan Tangan Menggunakan Algoritma Convolutional Neural Network dan K-Means Clustering. MALCOM: Indonesian Journal of Machine Learning and Computer Science, 4(4), 1646–1656. https://doi.org/10.57152/malcom.v4i4.1451
Toscana, A. Z., Setianingsih, C., & Paryasto, M. W. (2024). Integrasi Streamlit pada Aplikasi Berbasis Web dengan Algoritma YOLO V8 dan Teknologi Drone untuk Identifikasi Jenis dan Estimasi Tinggi Pohon. e-Proceeding of Engineering, 1828–1831. https://www.kdnuggets.com/2019/10/write-web-
Wahid, M. H., & Ujianto, E. I. H. (2024). Efficient Pattern Recognition of Sundanese Script Variants Using CNN. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 8(6), 808–818. https://doi.org/10.29207/resti.v8i6.6122
Wulandari, L. S., Rosalina, E., & Shomami, A. (2023). Adaptive Learning of Sundanese Script Based on Android Games in The Digital Era. P2M STKIP Siliwangi, 10(1), 25–39. https://doi.org/https://doi.org/10.22460/p2m.v10i1.3747
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Implementasi Convolutional Neural Network Untuk Pengenalan Tulisan Tangan Akasara Sunda Ngalangéna
Pages: 1037-1049
Copyright (c) 2025 Rahma Nur Azizah, Donny Avianto
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
