REKOMENDASI MODEL RAMBUT BERDASARKAN BENTUK WAJAH MENGGUNAKAN METODE CNN
DOI:
https://doi.org/10.29407/kmnyqa96Abstract
Perkembangan Artificial Intelligence telah mendorong pemanfaatan teknologi Computer Vision dalam berbagai bidang, termasuk pengembangan sistem rekomendasi berbasis citra. Salah satu permasalahan yang masih sering dijumpai adalah pemilihan model rambut yang kurang sesuai dengan bentuk wajah karena umumnya dilakukan berdasarkan preferensi pribadi atau rekomendasi penata rambut yang bersifat subjektif. Penelitian ini bertujuan mengembangkan aplikasi rekomendasi model rambut berdasarkan bentuk wajah menggunakan metode Convolutional Neural Network (CNN). Implementasi CNN dilakukan menggunakan arsitektur MobileNetV2 melalui pendekatan transfer learning untuk mengoptimalkan proses klasifikasi dengan kebutuhan komputasi yang relatif rendah. Dataset penelitian terdiri atas 4.000 citra wajah yang dikelompokkan ke dalam empat kategori, yaitu Heart, Oval, Round, dan Square. Sebelum proses pelatihan dilakukan, seluruh citra melalui tahap preprocessing berupa resize, normalisasi, dan data augmentation pada data latih. Model yang telah dilatih kemudian diintegrasikan ke dalam aplikasi berbasis web menggunakan Flask sehingga pengguna dapat mengunggah citra wajah dan memperoleh hasil klasifikasi beserta rekomendasi model rambut secara otomatis. Hasil pengujian terhadap 600 data testing menunjukkan bahwa model memperoleh nilai accuracy sebesar 57%, precision sebesar 58%, recall sebesar 57%, dan F1-score sebesar 56%. Selain menghasilkan klasifikasi bentuk wajah, aplikasi juga menampilkan tingkat kepercayaan (confidence) serta beberapa alternatif model rambut yang sesuai dengan hasil prediksi. Hasil penelitian menunjukkan bahwa integrasi metode CNN dengan aplikasi berbasis web mampu memberikan rekomendasi model rambut secara praktis serta berpotensi menjadi solusi pendukung dalam membantu pengguna menentukan model rambut yang sesuai dengan karakteristik wajah.
Keywords:
Computer Vision, CNN, Klasifikasi Wajah, Potongan Rambut, Sistem Rekomendasi.##plugins.themes.default.displayStats.downloads##
References
[1] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep
Convolutional Neural Networks,” Communications of the ACM, vol. 60, no. 6, pp. 84–
90, 2017.
[2] K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image
Recognition,” in Proceedings of the IEEE Conference on Computer Vision and Pattern
Recognition, 2016, pp. 770–778.
[3] A. G. Howard et al., “MobileNets: Efficient Convolutional Neural Networks for
Mobile Vision Applications,” 2017.
[4] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “MobileNetV2:
Inverted Residuals and Linear Bottlenecks,” in Proceedings of the IEEE/CVF
Conference on Computer Vision and Pattern Recognition, 2018, pp. 4510–4520.
[5] F. Chollet, Deep Learning with Python, 2nd ed. Shelter Island, NY, USA: Manning
Publications, 2021.
[6] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA:
MIT Press.
[7] 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, 2024.
[8] S. Hajar, M. Murinto, and A. Yudhana, “Comparison of Transfer Learning Strategies
Using MobileNetV2 and ResNet50 for Image Classification,” JUTIF, vol. 6, no. 5, 2025.
[9] N. H. Muttaqin et al., “Transfer Learning-Based CNN for Facial Image
Classification,” Jurnal Ilmu Komputer dan Informatika, 2025.
[10] Y. Chen, Y. Zhang, Z. Huang, Z. Luo, and J. Chen, “CelebHair: A Large-Scale
Dataset for Hairstyle Recommendation Based on CelebA,” 2021.
[11] T. Mikolov et al., “Transfer Learning in Deep Neural Networks: A Survey,” IEEE
Access, 2022.
[12] R. Szeliski, Computer Vision: Algorithms and Applications, 2nd ed. Springer, 2022.
[13] A. Rosebrock, Deep Learning for Computer Vision with Python. PyImageSearch,
2021.
[14] D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” in
International Conference on Learning Representations (ICLR), 2015.
[15] T. Fawcett, “An Introduction to ROC Analysis,” Pattern Recognition Letters, vol.
27, no. 8, pp. 861–874, 2006.
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
