PENERAPAN YOLOV13 UNTUK DETEKSI ALFABET BAHASA ISYARAT INDONESIA SECARA REAL-TIME
DOI:
https://doi.org/10.36080/skanika.v9i2.3872Keywords:
BISINDO, FullPAD, HyperAce, YOLOv13, Real-TimeAbstract
Indonesian Sign Language (BISINDO) is the primary communication medium for the deaf community. However, public understanding remains limited, and recognizing similar gestures and adapting to dynamic lighting pose significant challenges. This study applies the YOLOv13-Nano architecture with HyperACE and FullPAD modules for static BISINDO alphabet detection (A–Z). The model was trained on 5,835 images from the Mendeley Dataset (70:15:15 split) using MediaPipe Hands auto-labeling, and implemented on a FastAPI dashboard with debouncing and temporal auto-spacing logics. Offline testing shows YOLOv13-Nano achieved 89.22% classification accuracy, 83.02% mAP50, 90.63% Precision, 89.62% Recall, 89.74% F1-Score, and 23.62 ms inference time. This model outperforms K-Nearest Neighbors (KNN) baselines, where KNN (Full Image) achieved 9.90% accuracy and KNN (Hand Cropped) achieved 11.23% accuracy. Limited real-time testing on the test subject yielded a Word Accuracy of 87.4% under normal conditions, 88.3% under extreme low-light, and 90.4% alphabet accuracy against complex backgrounds. These results demonstrate the potential of YOLOv13-Nano to support a responsive real-time BISINDO translation system under various real-world environmental conditions.
Downloads
References
[1] Meysa Malika and Berlianti Berlianti, “Penggunaan Bahasa Isyarat SIBI dan BISINDO untuk Siswa Tuli di Sekolah Luar Biasa Negeri Pembina Medan,” Concept: Journal of Social Humanities and Education, vol. 4, no. 3, pp. 78–87, 2025, doi: 10.55606/concept.v4i3.2178.
[2] Badan Pusat Statistik, “Potret Penyandang Disabilitas di Indonesia: Hasil Long Form SP2020 - Badan Pusat Statistik Indonesia.” Accessed: Jan. 10, 2026. [Online]. Available: https://www.bps.go.id/id/publication/2024/12/20/43880dc0f8be5ab92199f8b9/potret-penyandang-disabilitas-di-indonesia--hasil-long-form-sp2020.html
[3] A. F. Muhammad and D. Andamisari, “Strategi Komunikasi Komunitas Gerakan Kesejahteraan Tunarungu Indonesia Dalam Menyosialisasikan Bahasa Isyarat Indonesia di Jakarta,” LUGAS Jurnal Komunikasi, vol. 8, no. 2, pp. 200–209, 2024, doi: 10.31334/lugas.v8i2.4727.
[4] M. Alaftekin, I. Pacal, and K. Cicek, “Real-time sign language recognition based on YOLO algorithm,” Neural Comput. Appl., vol. 36, no. 14, pp. 7609–7624, 2024, doi: 10.1007/s00521-024-09503-6.
[5] K. S. Adi, P. I. Afu, and P. W. Bondan, “Pengembangan Sistem Perhitungan Jumlah Kendaraan Berdasarkan Jenis Kendaraan Menggunakan Algoritma YOLO Secara Realtime,” SKANIKA: Sistem Komputer dan Teknik Informatika, vol. 7, pp. 166–178, 2024, doi: 10.36080/skanika.v7i2.3201.
[6] F. Farhana, A. R. E. Najaf, and R. Permatasari, “BISINDO Sign Language Interpreter System Using YOLOv8 and CNN,” bit-Tech, vol. 8, no. 1, pp. 598–607, 2025, doi: 10.32877/bt.v8i1.2638.
[7] N. Renaningtias, F. Putra Utama, A. Nur, and A. Sobri, “Deteksi Bahasa Isyarat Indonesia (BISINDO) Pada Video dengan YOLOv7,” JSAI: Journal Scientific and Applied Informatics, vol. 8, no. 1, 2025, doi: 10.36085/jsai.v8i1.7067.
[8] S. Azahra Putri, “Alphabet SIBI sign language recognition using YOLOv11 for real-time gesture detection,” vol. 11, no. 1, pp. 123–135, Jul. 2025, doi: 10.35335/mandiri.v14i1.408.
[9] A. Munandar, Z. Yunizar, and S. Retno, “Indonesian Sign Language (BISINDO) Alphabet Detection System Using YOLO (You Only Look Once) Algorithm,” Proceedings of MICoMS, vol. 4, pp. 1-10, 2024, doi: 10.29103/micoms.v4i.952.
[10] S. Daniels, N. Suciati, and C. Fathichah, “Indonesian Sign Language Recognition using YOLO Method,” IOP Conf. Ser. Mater. Sci. Eng., vol. 1077, 2021, doi: 10.1088/1757-899X/1077/1/012029.
[11] D. S. Ariansyah, “Pendeteksi Kata Dalam Bahasa Isyarat Menggunakan Algoritma YOLO VERSI 8,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 12, no. 3, pp. 2772-2778, 2024, doi: 10.23960/jitet.v12i3.4904.
[12] Y. Gao, et al., “Benchmarking YOLOv8 to YOLOv13 for robust hand gesture recognition in human–robot interaction,” Sci. Rep., vol. 15, no. 1, p. 40043, 2025, doi: 10.1038/s41598-025-23925-9.
[13] M. Lei et al., “YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception,” Cornell University, Sep. 2025, doi: 10.48550/arXiv.2506.17733.
[14] S. A. Sanjaya, “BISINDO Indonesian Sign Language: Alphabet Image Data,” vol. 1, 2024, doi: 10.17632/YWNJPBCZ8M.1.
[15] H. D. Rimbawa, et al., “Artificial intelligence-based hand gesture recognition for sign language interpretation,” Jurnal Mandiri IT, vol. 14, no. 1, pp. 76–86, 2025, doi; 10.35335/mandiri.v14i1.395.
[16] E. L. Kelana, M. Riko, A. Prasetya, and M. Zulfadhilah, “Integrating the CNN Model with the Web for Indonesian Sign Language (BISINDO) Recognition,” Journal of Applied Informatics and Computing (JAIC), vol. 9, no. 3, pp. 883–896, 2025, doi: 10.30871/jaic.v9i3.9345.
[17] D. Fan, et al., “Continuous sign language recognition algorithm based on object detection and variable-length coding sequence,” Sci. Rep., vol. 14, no. 1, pp. 1-21, 2024, doi: 10.1038/s41598-024-78319-0.
[18] M. L. Ali and Z. Zhang, “The YOLO Framework: A Comprehensive Review of Evolution, Applications, and Benchmarks in Object Detection,” Computers, vol. 13, no. 12, pp. 1-37, 2024, doi: 10.3390/computers13120336.
[19] L. T. Ramos and A. D. Sappa, “A Decade of You Only Look Once (YOLO) for Object Detection: A Review,” pp. 1-39, 2025, Institute of Electrical and Electronics Engineers Inc. doi: 10.1109/ACCESS.2025.3630988.
[20] K. Riehl, M. Neunteufel, and M. Hemberg, “Hierarchical confusion matrix for classification performance evaluation,” J. R. Stat. Soc. Ser. C Appl. Stat., vol. 72, no. 5, pp. 1394–1412, 2023, doi: 10.1093/jrsssc/qlad057.
[21] W. Shinta Sari and C. Atika Sari, “Klasifikasi Bunga Mawar Menggunakan KNN dan Ekstraksi Fitur GLCM dan HSV,” SKANIKA: Sistem Komputer dan Teknik Informatika, vol. 5, no. 2, pp. 145–156, 2022, doi: 10.36080/skanika.v5i2.2951.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Muhammad Noval Rais, Sawali Wahyu
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
CC BY-SA 4.0
Creative Commons Attribution-ShareAlike 4.0 International
This license requires that reusers give credit to the creator. It allows reusers to distribute, remix, adapt, and build upon the material in any medium or format, even for commercial purposes. If others remix, adapt, or build upon the material, they must license the modified material under identical terms.
BY: Credit must be given to you, the creator.
SA: Adaptations must be shared under the same terms.ng
