ANALISIS KINERJA YOLOV8S PADA DETEKSI CITRA HURUF STATIS SISTEM ISYARAT BAHASA INDONESIA
DOI:
https://doi.org/10.29407/dbm24b26Abstract
Sistem Isyarat Bahasa Indonesia digunakan sebagai sarana komunikasi visual bagi penyandang tunarungu, tetapi pengenalannya masih membutuhkan dukungan teknologi agar dapat dikenali secara otomatis melalui citra tangan. Penelitian ini bertujuan mengevaluasi kemampuan algoritma YOLOv8s dalam mendeteksi huruf SIBI secara real-time. Dataset yang digunakan terdiri dari 12672 citra dengan 24 kelas huruf, tanpa huruf J dan Z karena keduanya memiliki karakter gerakan dinamis. Tahapan penelitian meliputi pengumpulan dataset, pelabelan, prapemrosesan, pelatihan model, dan evaluasi menggunakan confusion matrix, precision, recall, F1 score, serta mAP. Hasil pengujian menunjukkan precision sebesar 0,9946, recall sebesar 0,9950, F1 score sebesar 0,9948, mAP50 sebesar 0,9907, dan mAP50-95 sebesar 0,7726. Hasil tersebut menunjukkan bahwa YOLOv8s mampu mendeteksi huruf SIBI dengan tingkat ketepatan yang tinggi.
Keywords:
Bahasa Isyarat, Computer Vision, Deteksi Huruf, SIBI, YOLOv8s##plugins.themes.default.displayStats.downloads##
References
[1] A. Taupiq, M. Wildan Fajri, and Dannylee, “Identification of Indonesian Sign
Language System Using Deep Learning in Yolo-based,” Media Journal of
General Computer Science, vol. 1, no. 2, pp. 40–47, Jun. 2024, doi:
10.62205/mjgcs.v1i2.22.
[2] D. Permana and J. Sutopo, “APLIKASI PENGENALAN ABJAD SISTEM
ISYARAT BAHASA INDONESIA (SIBI) DENGAN ALGORITMA YOLOv5
MOBILE APPLICATION ALPHABET RECOGNITION OF INDONESIAN
LANGUAGE SIGN SYSTEM (SIBI) USING YOLOv5 ALGORITHM,” Jurnal
SimanteC, vol. 11, no. 2, 2023, doi: 10.21107/simantec.v11i2.19783.
[3] H. Halim, “APLIKASI PENGIDENTIFIKASI BAHASA ISYARAT
BERDASARKAN GERAK TUBUH SECARA REAL TIME
MENGGUNAKAN YOLO,” Jurnal Sistem Informasi dan Teknik Komputer, vol.
8, no. 2, 2023, doi: 10.51876/simtek.v8i2.215.
[4] I. Inayatul Arifah, F. Nur Fajri, and G. Qorik Oktagalu Pratamasunu, “Deteksi
Tangan Otomatis Pada Video Percakapan Bahasa Isyarat Indonesia
Menggunakan Metode YOLO Dan CNN,” 2022. doi: 10.30871/jaic.v6i2.4694.
[5] L. Zholshiyeva, T. Zhukabayeva, A. Serek, R. Duisenbek, M. Berdieva, and N.
Shapay, “Deep Learning-Based Continuous Sign Language Recognition,”
Journal of Robotics and Control (JRC), vol. 6, no. 3, pp. 1106–1119, 2025, doi:
10.18196/jrc.v6i3.25881.
[6] M. Safaldin, N. Zaghden, and M. Mejdoub, “An Improved YOLOv8 to Detect
Moving Objects,” IEEE Access, vol. 12, pp. 59782–59806, 2024, doi:
10.1109/ACCESS.2024.3393835.
[7] L. Shen, B. Lang, and Z. Song, “DS-YOLOv8-Based Object Detection Method
for Remote Sensing Images,” IEEE Access, vol. 11, pp. 125122–125137, 2023,
doi: 10.1109/ACCESS.2023.3330844.
[8] D. S. Ariansyah, “PENDETEKSI KATA DALAM BAHASA ISYARAT
MENGGUNAKAN ALGORITMA YOLO VERSI 8,” Jurnal Informatika dan
Teknik Elektro Terapan, vol. 12, no. 3, Aug. 2024, doi:
10.23960/jitet.v12i3.4904.
[9] M. E. Wijaya and A. N. Handayani, “Integration of Yolov8 And Instance
Segmentation in The Chinese Sign Language (CSL) Recognition System,”
Indonesian Journal of Data and Science, vol. 6, no. 2, pp. 241–250, Jul. 2025,
doi: 10.56705/ijodas.v6i2.247.
[10] M. Y. and H. H. D. A. Faroek, “Image Processing and Object Detection in the
Indonesian Sign System (SIBI) for Hearing-Impaired Communication,” 2026.
doi: 10.30871/jaic.v10i1.11395.
[11] H. Yi, B. Liu, B. Zhao, and E. Liu, “Small Object Detection Algorithm Based on
Improved YOLOv8 for Remote Sensing,” IEEE J. Sel. Top. Appl. Earth Obs.
Remote Sens., vol. 17, pp. 1734–1747, 2024, doi:
10.1109/JSTARS.2023.3339235.
[12] L. Fitriani, D. Kurniadi, and I. S. Rajab, “Implementation of Machine Learning
Model to Detect Sign Language Movement in SIBI Learning Media,” Teknika,
vol. 14, no. 1, pp. 57–65, Mar. 2025, doi: 10.34148/teknika.v14i1.1159.
Downloads
Published
Issue
Section
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:
- Copyright on any article is retained by the author(s).
- 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.
- 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.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
