Performance Comparison of Facial Skin Type Classification Using the Segment Anything Model
DOI:
https://doi.org/10.57152/malcom.v6i2.2604Keywords:
CNN, Deep Learning, MobileNetv3, Segment Anything Model, Skin Type ClassificationAbstract
The facial skin is the first area to often experience various problems. Knowing one’s skin type is an important step in choosing the right skincare routine, but it can be difficult to determine accurately without a specialist's help, which can be costly. To address this, a deep learning approach can be applied to help automatically classify skin types. In this study, several combinations of CNN, MobileNetV3, and SAM models were applied and compared for facial skin type classification. The dataset used, sourced from the figshare platform, consists of 2,250 facial images representing 5 skin types: normal, dry, oily, sensitive, and combination. The dataset was divided into three parts: training (80%), validation (10%), and testing (10%). Each model was evaluated using a confusion matrix, with accuracy, precision, recall, and F1-score metrics used to determine and compare model performance. The results show that the CNN performed worst, while the MobileNetV3-based CNN was the best-performing model, achieving an accuracy of 97%. Meanwhile, adding SAM did not improve performance and actually decreased accuracy. This study demonstrates that using MobileNetV3 without segmentation is more effective than adding SAM segmentation for facial skin type classification.
Downloads
References
R. Oliveira, J. Ferreira, L. F. Azevedo, dan I. F. Almeida, “An Overview of Methods to Characterize Skin Type: Focus on Visual Rating Scales and Self Report Instruments,” MDPI, vol. 10, no. 1, hal. 1–15, 2023, doi: 10.3390/cosmetics10010014.
J. Ananta, “Gak Hanya Jerawat, Kulit Kusam Jadi Masalah Serius Perempuan Indonesia,” IDN TIMES. Tersedia pada: https://www.idntimes.com/life/women/kulit-kusam-jadi-masalah-perempuan-indonesia-00-p9v6l-2mqlbw
Riska Sahla Nafiah, E. Fitraneti, Y. Rizal, I. Primawati, dan ayu dian Hamama, “Pengaruh Paparan Sinar Ultraviolet terhadap Kesehatan Kulit dan Upaya Pencegahannya?: Tinjauan Literatur,” Sci. J., vol. 3, no. 3, hal. 185–194, 2024, doi: 10.56260/sciena.v3i3.147.
Anisa dian Agustina, “Klasifikasi Citra Jenis Kulit Wajah Dengan Algoritma Convolutional Neural Network (Cnn) Resnet-50,” JISSI, vol. 1, no. 3, hal. 2–8, 2024.
Sarah Nabila Hafni, Yuliana, dan A. Yulastri, “Literature Riview?: Hubungan Tingkat Pengetahuan Dengan Gaya Hidup Terhadap Kesehatan Kulit Wajah,” J. Penelit. imliah multidisiplin, vol. 8, no. 7, hal. 285–293, 2024.
L. Khodijah, R. Latifah, dan Y. Adharani, “Identifikasi Jenis Kulit Wajah Menggunakan K-Nearest Neighbor,” Sintaks, 2022.
P. S. Parraga et al., “Skin type classifications?: does the perfect assessment exist??,” J. Dermatolog. Treat., vol. 35, no. 1, hal. 1471–1753, 2024, doi: 10.1080/09546634.2024.2427325.
Shinta Dewi Kusumaningrum dan I. Muhimmah, “Analisis Faktor dan Metode Untuk Menentukan Tipe Kulit Wajah?: Tinjauan Literatur,” JTIIK, vol. 10, no. 4, hal. 753–762, 2023, doi: 10.25126/jtiik.2023106955.
T. Anoushkaa, K. V Dikshitha, P. lakshmi Pranitha, dan K. Vaidehi, “Deep Learning in Dermatology: A Review on Skin Type Classification and Disease Detection,” Interantional J. Sci. Res. Eng. Manag., vol. 09, no. 03, hal. 1–9, 2025, doi: 10.55041/ijsrem42607.
S. Cahyaningsih, A. Triayudi, dan I. D. Sholihati, “Kombinasi Metode Certainty Factor dan Forward Chaining untuk Identifikasi Jenis Kulit Wajah Berbasis Android,” J. Media Inform. Budidarma, vol. 5, no. 1, hal. 74, 2021, doi: 10.30865/mib.v5i1.2591.
R. A. Dianto, T. F. Anggraeny, dan H. Maulana, “Analisis Efektifitas Algoritma Mobilenetv3-large dan efficientnet-b0 untuk klasifikasi citra penyakit daun jeruk,” JITET, vol. 13, no. 3, 2025.
D. P. Sinaga dan N. Khairina, “Penerapan Mobilenetv3 Untuk Klasifikasi Jenis Bahan Pakaian,” INCODING J. Inform. Comput. Sci. Eng., vol. 4, no. 1, hal. 1–8, 2024, doi: 10.34007/incoding.v4i1.469.
S. Dewi, F. Ramadhani, dan S. Djasmayena, “View of Klasifikasi Jenis Jerawat Berdasarkan Gambar Menggunakan Algoritma CNN (Convolutional Neural Network),” 2024.
Herimanto, A. S. Dharma, J. Amalia, D. Largo, dan C. A. P. Sihite, “Kinerjance Analysis of MobileNetV3-based Convolutional Neural,” RESTI, vol. 5, no. 158, hal. 701–709, 2024, doi: https://doi.org/10.29207/resti.v8i6.5982.
J. Zhang, F. Zhoung, K. He, M. Ji, dan C. Li, “Recent Advancements and Perspectives in the Diagnosis of Skin Diseases Using Machine Learning and Deep Learning?: A Review,” 2023.
A. Baroroh dan H. Harintaka, “Ekstraksi Otomatis Tapak Bangunan (Building Footprint) Pada Ortofoto Menggunakan Segment Anything Model (Sam),” Elipsoida J. Geod. dan Geomatika, vol. 8, no. 1, hal. 52–59, 2025, doi: 10.14710/elipsoida.2025.25145.
L. Lutviana, Rian Ardianto, dan Purwono, “CNN-based Classification of Bladder Tissue Lesions from Endoscopy Images,” IT J. Res. Dev., vol. 9, no. 2, hal. 95–107, 2025, doi: 10.25299/itjrd.2025.17867.
M. Fadhilla, D. Suryani, A. Labellapansa, dan H. Gunawan, “Corn Leaf Diseases Recognition Based on Convolutional Neural Network,” IT J. Res. Dev., vol. 8, no. 1, hal. 14–21, 2023, doi: 10.25299/itjrd.2023.13904.
Prima A. Gani dan E. Poerwandono, “Pengembangan Aplikasi Android Berbasis Machine Learning Untuk Pendeteksi Jenis Kulit Wajah Menggunakan Deep Learning,” JATI, vol. 9, no. 6, hal. 9551–9557, 2025, doi: https://doi.org/10.36040/jati.v9i6.15674.
E. Moupojou, F. Retraint, H. Tapamo, M. Nkenlifack, C. Kacfah, dan A. Tagne, “Segment Anything Model and Fully Convolutional Data Description for Plant Multi-Disease Detection on Field Images,” IEEE Access, vol. 12, no. July, hal. 102592–102605, 2024, doi: 10.1109/ACCESS.2024.3433495.
Y. Huang, X. Yang, L. Hiu, H. Zhou., A. Chang, dan X. Zhou, “Medical Image Analysis,” elsevier, 2024.
S. S. Arachchi, “skin type identification,” FIGSHARE. [Daring]. Tersedia pada: https://figshare.com/authors/Sanjana_Solanga_Arachchi/21778199
J. Deng, “The Data Preprocessing Technique in Machine Learning,” Sci. Technol. Eng. Chem. Environ. Prot., vol. 1, no. 10, hal. 1168–1172, 2024, doi: 10.61173/0hfqqz07.
R. Yohannes dan ezar M. Al Rivan, “Klasifikasi Jenis Kanker Kulit Menggunakan CNN-SVM,” J. Algoritm., vol. Vol.2, no. 2, hal. 1, 2022.
A. Luque, M. Mazzoleni, A. Carrasco, dan A. Febramosca, “Visualizing Classification Results?: Confusion Star and Confusion Gear,” IEEE Access, vol. 10, hal. 1659–1677, 2022, doi: 10.1109/ACCESS.2021.3137630.
M. Talaat, X. Si, dan J. Xi, “applied sciences Multi-Level Training and Testing of CNN Models in Diagnosing Multi-Center COVID-19 and Pneumonia,” MDPI, 2023.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Nisrina Nur Kumala, Asfan Muqtadir, Amaludin Arifia
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Copyright © by Author; Published by Institut Riset dan Publikasi Indonesia (IRPI)
This Indonesian Journal of Machine Learning and Computer Science is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
