Analisis Komparasi Otsu dan Adaptive Thresholding Pada Pengenalan Wajah Berbasis VGG16
DOI:
https://doi.org/10.29407/wwynv820Abstract
Pengenalan wajah merupakan teknologi biometrik yang banyak digunakan dalam sistem keamanan dan identifikasi digital. Penelitian ini bertujuan menganalisis pengaruh metode segmentasi citra terhadap kinerja sistem pengenalan wajah menggunakan Convolutional Neural Network (CNN) berbasis VGG16. Dataset yang digunakan terdiri dari 210 citra wajah yang ditingkatkan melalui augmentasi kecerahan menjadi 630 citra. Tahapan penelitian meliputi deteksi wajah menggunakan Haar Cascade, konversi grayscale, segmentasi menggunakan Otsu Thresholding dan Adaptive Thresholding, pelatihan model, serta evaluasi performa. Model dilatih menggunakan optimizer Adam selama 10 epoch. Evaluasi dilakukan menggunakan accuracy, confusion matrix, dan classification report. Hasil penelitian menunjukkan bahwa metode Otsu Thresholding memperoleh akurasi 90,32%, sedangkan Adaptive Thresholding mencapai 98,71% dengan performa yang lebih stabil. Sistem berhasil diimplementasikan pada aplikasi berbasis web menggunakan Streamlit untuk mendukung proses pengenalan wajah secara otomatis dan interaktif.
Keywords:
Pengenalan Wajah, Convolutional Neural Network, Adaptive Thresholding##plugins.themes.default.displayStats.downloads##
References
[1] E. Fatkhiyah, G. P. Sukmaputra, and R. Y. Ariyana, "Sistem Pengenalan Wajah Menggunakan Algoritma Convolutional Neural Network (CNN)," 2024. doi: 10.34151/prosidingsnast.v1i1.5108.
[2] N. Rinanto, R. A. Putri, M. Ardiana, A. Khumaidi, E. N. Sholikhah, and R. S. F. Jaelani Putra, "Sistem Deteksi dan Pengenalan Wajah Real-Time dengan Haar Cascade dan CNN Untuk Otomatisasi Kehadiran Mahasiswa," Jurnal Riset Rekayasa Elektro, vol. 7, no. 2, pp. 203-210, Dec. 2025, doi: 10.30595/jrre.v7i2.26563.
[3] D. Prayogi, S. R. Lubis, M. A. Rizko, and A. G. Suteja, "Optimalisasi Segmentasi Citra Digital Metode Canny Edge Detection dan Thresholding," RIGGS: Journal of Artificial Intelligence and Digital Business, vol. 4, no. 2, pp. 6334-6339, Jul. 2025, doi: 10.31004/riggs.v4i2.1613.
[4] Sanjaya I, Lelita T, and Yustiana I, "Application Of Vision Transformer For Identifying Indonesian Herbal Plants Based On Visual Images," Jurnal Media Computer Science, 2025, doi: 10.37676/jmcs.v4i2.
[5] Isvine Zahroya Jazmine Marzuki Fahd, Abdul Rabi, and Elta Sonalitha, "Perbandingan Akurasi Model ResNet50 dan VGG16 dalam Mengklasifikasi Penyakit Cacar Menggunakan Metode Convolutional Neural Network," Uranus: Jurnal Ilmiah Teknik Elektro, Sains dan Informatika, vol. 3, no. 1, pp. 170-180, Jan. 2025, doi: 10.61132/uranus.v3i1.679.
[6] M. Fawzan and D. Udjulawa, "Optimasi Hyperparameter CNN dengan Arsitektur VGG16 Menggunakan Grid Search Untuk Klasifikasi Penyakit Buah Delima," Arcitech: Journal of Computer Science and Artificial Intelligence, vol. 5, no. 2, pp. 306-331, Dec. 2025, doi: 10.29240/arcitech.v5i2.15175.
[7] L. Mahdiyah, S. Oktamuliani, and W. L. Putri, "Penerapan Algoritma Deep Learning YOLOv8 pada Platform Roboflow untuk Segmentasi Citra Panoramik," Jurnal Fisika Unand, vol. 14, no. 3, pp. 228-234, May 2025, doi: 10.25077/jfu.14.3.228-234.2025.
[8] D. B. D. Hanggoro, "Analisis Komparatif Arsitektur Deep Learning Untuk Aplikasi Computer Vision: Studi Literature Review," Jurnal Komputer Teknologi Informasi Sistem Informasi (JUKTISI), vol. 4, no. 2, pp. 1001-1008, Aug. 2025, doi: 10.62712/juktisi.v4i2.542.
[9] F. H. Adiba, P. Kasih, and M. A. D. W. Dara, "Implementation and Evaluation of the K - Nearest Neighbors Algorithm in Badminton Movement Classification," Jurnal SISFOKOM (Sistem Informasi dan Komputer), vol. 14, no. 4, Dec. 2025, doi: 10.32736/sisfokom.v14i4.2441.
[10] W. Mellyssa, "Penerapan Metode Otsu Thresholding Dan Koefisien Korelasi Pada Pendeteksian Judul Buku Tugas Akhir Judul Artikel," Jurnal Elektro dan Telekomunikasi Terapan, vol. 8, no. 1, p. 925, Jul. 2021, doi: 10.25124/jett.v8i1.3686.
[11] M. U. Habibah and M. Kurniawan, "Segmentasi Citra Wajah dengan Implementasi Adaptif Threshold-Integral Image," Oct. 2021, doi: 10.25126/jtiik.202183840.
[12] A. Antoni, T. Rohana, and A. R. Pratama, "Implementasi Algoritma Convolutional Neural Network Untuk Klasifikasi Citra Kemasan Kardus Defect dan No Defect," Building of Informatics, Technology and Science (BITS), vol. 4, no. 4, Mar. 2023, doi: 10.47065/bits.v4i4.3270.
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
