Implementasi YOLOv8 dan FaceNet untuk Sistem Keamanan Real-Time Berbasis IoT
DOI:
https://doi.org/10.22441/format.2026.v15.i1.009Kata Kunci:
CCTV, Deteksi Wajah, ESP32-CAM, FaceNet, Internet Of Things, YOLOv8,Abstrak
Sistem keamanan CCTV konvensional umumnya hanya berfungsi sebagai perekam pasif tanpa kemampuan analisis otomatis, yang menyebabkan keterlambatan deteksi karena proses identifikasi dilakukan secara manual. Keterbatasan ini menimbulkan latensi tinggi dan akurasi deteksi yang rendah, sehingga menjadi masalah krusial dalam kebutuhan keamanan modern. System keamanan yang baik dapat mencegah tindak kejahatan yang bisa merugikan penghuni rumah baik fisik maupun materiil. Penelitian ini mengusulkan pengembangan sistem keamanan cerdas berbasis Internet Of Things (IoT) dengan integrasi deteksi wajah menggunakan YOLOv8 dan pengenalan wajah FaceNet menggunakan modul ESP32-CAM. Sistem ini dirancang untuk mendeteksi wajah secara real-time, identifikasi individu secara otomatis, serta pengiriman notifikasi instan melalui Telegram ketika terdeteksi wajah yang tidak dikenal. Metode penelitian ini meliputi perancangan arsitektur IoT, pengambilan dataset wajah, preprocessing menggunakan MTCNN, FaceNet untuk menghasilkan facial embeddings, serta implementasi YOLOv8 sebagai detektor wajah real-time. Evaluasi kinerja pengenalan wajah dilakukan dengan menerapkan metode 5-fold cross-validation pada dataset embedding FaceNet menggunakan pengklasifikasi k-NN. Hasil eksperimen menunjukan bahwa sistem mampu mendeteksi wajah dengan tingkat respon tinggi dan mengenali individu dengan akurasi yang konsisten pada pencahayaan dan jarak bervariasi. Hasil pengujian training rata-rata accuracy Top-1 mencapai 0.96 dan rata-rata accuracy Top-5 sebesar 0.99, YOLOv8 menunjukkan kemampuan deteksi wajah yang akurat dan cepat dengan waktu respon 1,86 detik pada server berbasis CPU Intel Core i5 dan GPU Intel UHD Graphics 620. Performa pengujian akurasi FaceNet dengan pengklasifikasi k-NN menghasilkan akurasi 99.35%, presisi 99,35%, recall 98,94%, F1-score 99,11%, dan FPR (False Positive Rate) 0,08%, hal ini menunjukkan bahwa sistem memiliki akurasi pengenalan wajah yang sangat tinggi dan konsisten. Sistem yang dikembangkan mampu memberikan peringatan instan kepada pengguna melalui Telegram saat terdeteksi wajah yang tidak dikenal, sehingga meningkatkan waktu respons terhadap potensi ancaman. Dengan performa yang stabil dan tangguh serta biaya implementasi yang rendah, sistem ini menawarkan solusi keamanan modern yang lebih adaptif, proaktif, efektif, dan efisien dibandingkan CCTV konvensional.Unduhan
Referensi
H. Syafutra, T. Muhammad Nur Aziz, I. Novianty, M. Chusnu, and D. Prayoga, “Implementasi Sistem Keamanan Pintu Otomatis Berbasis Face Recognition di Proactive Robotic: Integrasi ESP32-Cam dan Telegram,” Jurnal Riset Fisika Indonesia, vol. 4, no. 2, 2024, [Online]. Available: https://journal.ubb.ac.id/jrfi/article/view/5380Halaman|65
G. Firmasyah, A. Mulyo Widodo, B. Tjahjono, and U. Esa Unggul, “PREVENTING CHILD KIDNAPING AT HOME USING CCTV THAT UTILIZES FACE RECOGNITION WITH YOU ONLY LOOK ONCE (YOLO) ALGORITHM”, [Online]. Available: http://ijsr.internationaljournallabs.com/index.php/ijsr
D. Anugrah Pratama and M. Bahrul Ulum, “RANCANG BANGUN SISTEM KEAMANAN RUMAH DENGAN FACE RECOGNITION BERBASIS ESP32-CAM 1,*),” 2024.
F. Schroff, D. Kalenichenko, and J. Philbin, “FaceNet: A Unified Embedding for Face Recognition and Clustering,” Jun. 2015, doi: 10.1109/CVPR.2015.7298682.
W. A. Shobaki and M. Milanova, “A Comparative Study of YOLO, SSD, Faster R-CNN, and More for Optimized Eye-Gaze Writing,” Sci, vol. 7, no. 2, Jun. 2025, doi: 10.3390/sci7020047.
A. Setiawan, K. T. Prasetyo, A. Rusdyansyah, and D. Ardian, “Implementation of facial recognition technology in the verification system for api banyuwangi cadets using the haar cascade algorithm,” Bulletin of Social Informatics Theory and Application, vol. 8, no. 2, pp. 309–330, Dec. 2024, doi: 10.31763/businta.v8i2.778.
D. P. Sari, “Comparative Study: Performance Comparison of You Only Look Once and Convolutional Neural Networks Algorithms in Human Object Detection,” Indonesian Journal of Artificial Intelligence and Data Mining (IJAIDM), vol. 8, no. 2, pp. 123–135, 2025, [Online]. Available: https://ejournal.uin-suska.ac.id/index.php/IJAIDM/article/view/37676
A. Nemavhola, C. Chibaya, and S. Viriri, “A Systematic Review of CNN Architectures, Databases, Performance Metrics, and Applications in Face Recognition,” Feb. 01, 2025, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/info16020107.
M. R. Dewanto, M. N. Farid, M. A. Rafdi Syah, A. A. Firdaus, and H. Arof, “YOLO vs. CNN Algorithms: A Comparative Study in Masked Face Recognition,” Scientific Journal of Informatics, vol. 11, no. 1, pp. 139–146, Feb. 2024, doi: 10.15294/sji.v11i1.48723.
G. Fairuz Mumtaz, J. Zeniarja, A. Luthfiarta, and A. N. Imam Muttaqin, “Optimizing Face Recognition and Emotion Detection in Student Identification Using FaceNet and YOLOv8 Models,” Inform : Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi, vol. 10, no. 1, pp. 34–44, Jan. 2025, doi: 10.25139/inform.v10i1.9304.
H. Lin, Y. Hu, S. Chen, J. Yao, and L. Zhang, “Fine-Grained Classification of Cervical Cells Using Morphological and Appearance Based Convolutional Neural Networks,” Oct. 2018, [Online]. Available: http://arxiv.org/abs/1810.06058
M. S. Uzer, “Deep Learning-Based Classification Consisting of Pre-Trained Models and Proposed Model Using K-Fold Cross-Validation for Pistachio Species,” Applied Sciences (Switzerland), vol. 15, no. 8, Apr. 2025, doi: 10.3390/app15084516.
C. Baretina, S. Saripudin, R. Listiana, and E. Damayanti, “Rancang Bangun Sistem Smart Door Lock Menggunakan Deteksi Wajah.”
C. I. Zamorano, K. Prawiroredjo, E. S. Julian, and E. Djuana, “Rancang Bangun Sistem Kamera Pengawas dengan Pengenalan Wajah untuk Keamanan Berbasis Blynk Legacy.”
A. M. S. M. Koroy, G. Mandar, and A. H. Muhammad, “RANCANG BANGUN SISTEM KEAMANAN PINTU RUMAH MENGGUNAKAN ESP32-CAM,” Jurnal Teknik Informatika (J-Tifa), vol. 3, no. 2, pp. 32–36, Sep. 2020, doi: 10.52046/j-tifa.v3i2.1038.
A. Peryanto, A. Yudhana, and D. R. Umar, “Rancang Bangun Klasifikasi Citra Dengan Teknologi Deep Learning Berbasis Metode Convolutional Neural Network,” 2019. [Online]. Available: https://www.mathworks.com/discovery/convolutional-neural-network.html
A. M. S. M. Koroy, G. Mandar, and A. H. Muhammad, “RANCANG BANGUN SISTEM KEAMANAN PINTU RUMAH MENGGUNAKAN ESP32-CAM,” Jurnal Teknik Informatika (J-Tifa), vol. 3, no. 2, pp. 32–36, Sep. 2020, doi: 10.52046/j-tifa.v3i2.1038.
M. Akbar Syahbana Pane et al., “Journal of Information System and Technology Research Low-Cost CCTV for Home Security With Face Detection Base on IoT,” 2024. [Online]. Available: http://creativecommons.org/licenses/by-sa/4.0/
C. Ferry, M. Saputra, and W. Sulistyo, “Alat Keamanan Depan Rumah Berbasis Internet of Things (IoT) Menggunakan ESP32-CAM yang Terintegrasi dengan Face Detection dan Telegram,” Jurnal Teknologi Informasi dan Komunikasi), vol. 8, no. 1, p. 2024, 2024, doi: 10.35870/jti.
A. P. Y. Waroh, N. Sajangbati, S. Sawidin, M. A. S. Kondoj, and T. J. Wungkana, “Sistem Keamanan Rumah Melalui Pengenalan Wajah Dengan Webcam Berbasis Raspberry Pi4,” Jambura Journal of Electrical and Electronics Engineering, vol. 7.
Unduhan
File Tambahan
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
The copyright to this article is transferred to Universitas Mercu Buana (UMB) if and when the article is accepted for publication. The undersigned hereby transfers any and all rights in and to the paper including without limitation all copyrights to UMB. The undersigned hereby represents and warrants that the paper is original and that he/she is the author of the paper, except for material that is clearly identified as to its original source, with permission notices from the copyright owners where required. The undersigned represents that he/she has the power and authority to make and execute this assignment.
We declare that this paper has not been published in the same form elsewhere.
Furthermore, I/We hereby transfer the unlimited rights of publication of the above-mentioned paper as a whole to UMB. The copyright transfer covers the right to reproduce and distribute the article, including reprints, translations, photographic reproductions, microform, electronic form (offline, online) or any other reproductions of similar nature.
The corresponding author signs for and accepts responsibility for releasing this material on behalf of any and all co-authors. This agreement is to be signed by at least one of the authors who have obtained the assent of the co-author(s) where applicable. After submission of this agreement signed by the corresponding author, changes of authorship or in the order of the authors listed will not be accepted.
Retained Rights/Terms and Conditions
Although authors are permitted to re-use all or portions of the Work in other works, this does not include granting third-party requests for reprinting, republishing, or other types of re-use.
Our Articles are licensed under CC BY-NC
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
