Sistem Klasifikasi Bentuk Wajah Menggunakan EfficientNet-B4 untuk Rekomendasi Gaya Rambut Berbasis Web
Abstract
The suitability of a hairstyle is largely influenced by the shape of a person's face; however, manual identification can often lack consistency due to the observer's subjectivity. This study developed an automated system designed to classify face shapes using the EfficientNet-B4 model, categorizing them into five types: Heart, Oblong, Oval, Round, and Square. The model was trained on a dataset of 27,066 labeled images, which included 19,926 images for training, 3,512 for validation, and 3,628 for testing. The training process involved a two-phase transfer learning approach: first, training the head of the model, followed by fine-tuning the backbone. To enhance performance and mitigate overfitting, data augmentation, learning rate scheduling, and early stopping techniques were utilized. Evaluation results revealed exceptional performance, achieving a validation accuracy of 96. 10%, a test accuracy of 93. 52%, and a macro-F1 score of 0. 935. The highest errors were found in the Oval and Oblong categories, whereas the Square category demonstrated the most consistency. This system is implemented in a web application utilizing Next. js and Express, where face detection is carried out on the client-side using react-webcam and face-api. js. Additionally, the system provides a hairstyle preview to enhance the user experience.
Keywords: EfficientNet-B4, face shape classification, hairstyle recommendation, transfer learning, web application.
Full Text:
PDFReferences
M. Y. Putra, “Rancang Bangun Deteksi Bentuk Wajah Untuk Menentukan Gaya Rambut Menggunakan Algoritma CNN,” Repeater : Publikasi Teknik Informatika dan Jaringan, vol. 2, no. 3, pp. 206–212, Jul. 2024, doi: 10.62951/repeater.v2i3.139.
A. Maghfiroh, I. Nurhayati, N. Atikah, M. I. Putri, and M. J. Nabila, “Pengaruh Media Sosial Terhadap Pemilihan Pangkas Rambut Desain Sesuai Dengan Bentuk Wajah,” JURNAL MULTIDISIPLIN ILMU AKADEMIK, vol. 2, no. 3, pp. 11–20, May 2025, doi: 10.61722/jmia.v2i3.4448.
V. Ramadhan, M. W. Sardjono, M. Cahyanti, E. R. Swedia, and M. R. D. Septian, “Klasifikasi Bentuk Bingkai (Frame) Kacamata Menggunakan CNN dengan Arsitektur Inception V3 dan Augmented Reality Berbasis Android,” Journal of System and Computer Engineering (JSCE) ISSN, vol. 5, no. 2, pp. 204–218, 2024, doi: 10.61628/jsce.v5i2.1292.
J. C. Wicaksono, J. Sahertian, and R. H. Irawan, “Klasifikasi Bentuk Wajah Menggunakan Efficientnet-B4,” Prosiding SEMNAS INOTEK (Seminar Nasional Inovasi Teknologi), vol. 9, pp. 2119–2127, 2025, Accessed: Nov. 28, 2025. [Online]. Available: https://proceeding.unpkediri.ac.id/index.php/inotek/
R. Imanuel, R. N. W. Dafalah, R. C. P. Murdoko, F. Budiman, and M. Muslih, “Deteksi Dan Klasifikasi Citra Wajah Menggunakan MTCNN Dan MOBILENET,” Integrative Research in Computer Science, vol. 1, no. 1, pp. 23–39, 2025, Accessed: Nov. 28, 2025. [Online]. Available: https://ritecs.org/journal/index.php/IRCS/article/view/4
A. Dhiya ’Ulhaq and I. K. D. Nuryana, “Sistem Rekomendasi Gaya Rambut Personal Berdasarkan Analisis Wajah dan Rambut,” JINACS: Journal of Informatics and Computer Science, vol. 07, no. 1, pp. 340–347, 2025, Accessed: Nov. 28, 2025. [Online]. Available: https://ejournal.unesa.ac.id/index.php/jinacs/article/view/72775
S. Mewandari et al., “Implementasi Framework Flutter Untuk Aplikasi Rekomendasi Gaya Rambut Menggunakan Artificial Intelegence Vision Chatgpt,” Jurnal Mahasiswa Teknik Informatika, vol. 8, no. 3, pp. 4026–4032, Jun. 2024, doi: 10.36040/jati.v8i3.9800.
F. A. J. Handani, E. Wijayanti, and R. Fiati, “Implementation Of Convolutional Neural Network Method In Classifying Pandawa Shadow Puppets,” Jurnal Teknik Informatika (Jutif), vol. 6, no. 1, pp. 211–219, Feb. 2025, doi: 10.52436/1.jutif.2025.6.1.1851.
M. Wasil, Harianto, and Fathurrahman, “Pengaruh Epoch pada Akurasi menggunakan Convolutional Neural Network untuk Klasifikasi fashion dan Furniture,” Infotek: Jurnal Informatika dan Teknologi, vol. 5, no. 1, pp. 53–61, Jan. 2022, doi: 10.29408/jit.v5i1.4393.
Moch. F. Alfathoni, I. Kadir, and A. Ma’ruf, “Penerapan Arsitektur Modern Pada Gedung Pusat Pendidikan Modeling Dan Fashion Designer Di Kota Kendari,” GARIS: Jurnal Mahasiswa Jurusan Arsitektur, vol. 9, no. 2, pp. 58–64, Aug. 2024, Accessed: Nov. 27, 2025. [Online]. Available: https://garis.uho.ac.id/index.php/journal/article/view/155
M. S. Azzahra, S. S. Maesaroh, and R. G. Guntara, “Penggunaan Convolutional Neural Network dan Transfer Learning untuk Rekomendasi Gaya Rambut Pria,” Jurnal Algoritma, vol. 21, no. 2, pp. 173–183, Nov. 2024, doi: 10.33364/algoritma/v.21-2.2134.
A. Z. Pramuditha, Suroso, and M. Fadhli, “Deteksi Wajah Dengan Model Arsitektur VGG 19 Pada Metode Convolutional Neural Network,” Sistemasi: Jurnal Sistem Informasi, vol. 13, no. 5, pp. 1998–2007, 2024, doi: 10.32520/stmsi.v13i5.4399.
M. M. Santoni, N. Chamidah, and D. S. Prasvita, “Strategi Ensemble Deep Learning pada Global Multi-Scale dan Local Attention Features pada Pengenalan Ekspresi Wajah,” Krea-TIF: Jurnal Teknik Informatika, vol. 12, no. 1, pp. 12–23, 2024, doi: 10.32832/krea-tif.v12i1.16287.
DOI: http://dx.doi.org/10.30829/algoritma.v9i2.26763
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Indexing:
 |  |  |  |
|
Algoritma: Jurnal Ilmu Komputer dan Informatika
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.