Penerapan Convolutional Neural Network (CNN) untuk Pengenalan Huruf Braille dari Citra ke Teks Abjad

Authors

  • Virganda Rimba Asmara Universitas Islam Balitar Indonesia
  • Abdi Pandu Kusuma Universitas Islam Balitar Indonesia
  • Wahyu Dwi Puspitasari Universitas Islam Balitar Indonesia

DOI:

https://doi.org/10.29407/g1pdxn97

Abstract

Huruf Braille merupakan media baca utama bagi penyandang tunanetra, namun tidak semua masyarakat mampu memahami dan menerjemahkannya. Penelitian ini bertujuan menerapkan metode Convolutional Neural Network (CNN) untuk mengenali huruf Braille dari citra digital menjadi teks abjad. Sistem dikembangkan menggunakan Python dengan TensorFlow, Keras, OpenCV, dan NumPy. Tahapan penelitian meliputi preprocessing citra berupa grayscale, median blur, adaptive thresholding, resize, dan normalisasi, kemudian dilanjutkan dengan pelatihan serta pengujian model. Evaluasi dilakukan menggunakan confusion matrix dan classification report. Hasil penelitian menunjukkan model mencapai akurasi sebesar 91% pada 1628 citra Braille. Sistem berhasil mengenali 23 dari 26 alfabet Braille, sedangkan huruf f, h, dan j masih sulit dikenali secara konsisten. Selain menghasilkan teks, sistem juga mampu mengubah hasil identifikasi menjadi suara. Hasil penelitian menunjukkan bahwa metode CNN efektif untuk pengenalan huruf Braille berbasis citra digital.

Keywords:

Convolutional Neural Network, Deep Learning, Huruf Braille, Pengenalan Citra, Text-to-Voice.

##plugins.themes.default.displayStats.downloads##

##plugins.themes.default.displayStats.noStats##

References

[1] A. Awang, I. Farahana, A. Rani, dan K. E. Hock, “Systematic Literature Review On

Braille Literacy in Special Education: Challenges and Braille Education Strategies,”

International Journal of Islamic Theology and Civilisation, vol. 3, no. 3, 2025, doi:

10.5281/zenodo.15554241.

[2] M. J. Burton dkk., “The Lancet Global Health Commission on Global Eye Health: vision

beyond 2020,” 1 April 2021, Elsevier Ltd. doi: 10.1016/S2214-109X(20)30488-5.

[3] I. G. Ovodov dan R. Zelenograd, “Optical Braille Recognition Using Object Detection

Neural Network,” Okt 2021, hlm. 1741–1748. doi: 10.1109/ICCVW54120.2021.00200.

[4] T. Kausar, S. Manzoor, A. Kausar, Y. Lu, M. Wasif, dan M. Adnan Ashraf, “Deep

Learning Strategy for Braille Character Recognition,” IEEE Access, vol. 9, hlm. 169357–169371,

2021, doi: 10.1109/ACCESS.2021.3138240.

[5] I. M. A. D. Suarjaya, B. A. Wiratama, dan A. Wirdiani, “Sistem Pengenalan Huruf Braille

Menggunakan Metode Deep Learning Berbasis Website,” JITSI : Jurnal Ilmiah Teknologi Sistem

Informasi, vol. 5, no. 3, hlm. 93–99, Jul 2024, doi: 10.62527/jitsi.5.3.244.

[6] A. Ridwan, Y. Purbolingga, dan H. Hanisah, “Utilizing Convolutional Neural Network

for Learning Web-Based Braille Letter Classification System,” Journal of Computer Networks,

Architecture and High Performance Computing, vol. 6, no. 1, Jan 2024, doi:

10.47709/cnahpc.v6i1.3386.

[7] K. M. Afriyanto dan A. Setiawan, “Pengenalan Gambar Braille Menggunakan Depthwise

Separable Convolutional Neural Network,” Techno.Com, vol. 24, no. 2, hlm. 355–364, Mei 2025,

doi: 10.62411/tc.v24i2.12445.

[8] R. A. Himawan, E. H. Rachmawanto, dan C. A. Sari, “Real-Time Braille Letter Detection

System Using YOLOv8,” 2025. [Daring]. Tersedia pada:

http://jurnal.polibatam.ac.id/index.php/JAIC

[9] R. Noviyanti dan E. Sinduningrum, “Braille Character Recognition with Histogram of

Oriented Gradient (HOG) and SVM-Based Image Processing,” Syntax Literate: Jurnal Ilmiah

Indonesia, vol. 9, no. 8, 2024, doi: 10.36418/syntax-literate.v9i8.

[10] M. Andriansyah dan H. Junaedi, “Pengenalan Karakter Braille Memanfaatkan

Convolutional Neural Network,” Jurnal Konvergensi, Institut Sains dan Teknologi Terpadu

Surabaya (ITSI), vol. 17, no. 2, hlm. 56, Jul 2021, doi: https://doi.org/10.30996/konv.v17i2.5420.

Downloads

Published

2026-07-20

Issue

Vol. 10 No. 2 (2026): Prosiding Seminar Nasional Inovasi Teknologi Tahun 2026

Section

Articles

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Authors who publish with this journal agree to the following terms:

  1. Copyright on any article is retained by the author(s).
  2. The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
  3. 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.
  4. 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.
  5. The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License

How to Cite

Penerapan Convolutional Neural Network (CNN) untuk Pengenalan Huruf Braille dari Citra ke Teks Abjad. (2026). Prosiding SEMNAS INOTEK (Seminar Nasional Inovasi Teknologi), 10(2), 1318-1327. https://doi.org/10.29407/g1pdxn97