Sistem Klasifikasi Tingkat Keparahan Jerawat Berdasarkan Jenis Jerawat Menggunakan CNN
DOI:
https://doi.org/10.29407/9867qj40Keywords:
CNN, Deep Learning, Jerawat, Klasifikasi Citra, MobileNetV2Abstract
Jerawat merupakan salah satu gangguan kulit yang umum terjadi dan sering menimbulkan masalah estetika maupun psikologis. Variasi bentuk dan tingkat keparahan jerawat menyebabkan proses identifikasi manual menjadi tidak konsisten, sehingga diperlukan sistem otomatis berbasis kecerdasan buatan. Penelitian ini bertujuan untuk mengembangkan sistem klasifikasi jenis jerawat menggunakan metode Convolutional Neural Network (CNN) dengan arsitektur MobileNetV2. Dataset bersumber dari Roboflow dan Kaggle sebanyak 2.000 citra wajah yang terdiri atas empat kelas, yaitu whitehead, papula, pustula, dan nodul. Data melalui tahap resizing, normalisasi, dan augmentasi, kemudian dibagi menjadi 80% untuk pelatihan dan 20% untuk pengujian. Proses pelatihan dilakukan selama 50 epoch menggunakan optimizer Adam dengan learning rate 0.0001. Hasil penelitian menunjukkan bahwa model CNN mampu mengklasifikasikan citra jerawat dengan baik dengan akurasi 85,25%, precision 85,73%, recall 84,90%, dan F1-score 85,31%. Kelas whitehead dan papula memperoleh hasil terbaik, sementara kesalahan terbanyak terjadi antara pustula dan nodul. Hasil ini menunjukkan bahwa arsitektur MobileNetV2 efektif untuk klasifikasi otomatis jerawat dan berpotensi dikembangkan sebagai alat bantu diagnosis berbasis kecerdasan buatan dalam bidang teledermatologi.
Downloads
References
[1] Odho, A. A., Bilal, A., & Malik, N. U. R. (2025). Skin Acne Skin Disease Classification by Using Fine Tuned Convolutional Neural Network. SES Journal, 3(4), 639–646.
[2] Traini, D. O., Palmisano, G., Guerriero, C., & Peris, K. (2025). Artificial Intelligence in the Assessment and Grading of Acne Vulgaris: A Systematic Review. Journal of Personalized Medicine, 15(6), 238
[3] Watanabe, K., Iinuma, K., Nakashima, C., et al. (2025). Deep Learning-Based Acne Severity Classification Using Standardized Facial Images of Japanese Patients. Cureus, 17(9), e91944. DOI: 10.7759/cureus.91944
[4] Hasanah, R. L., Rianto, Y., & Riana, D. (2022). Identification of Acne Vulgaris Type in Facial Acne Images Using GLCM Feature Extraction and Extreme Learning Machine Algorithm. Rekayasa, 15(2), 204–214
[5] Shaik, A., Kanichai, J. J., Kurumthottam, A. B., Garg, V., & Ananthakrishnan, B. (2025). An Experimental Evaluation of Deep Learning-Based Models for Acne Severity Classification in Humans. Connection Science, 37(1), 2533867.
[6] Sebayang, V. D. B., & Kusuma, I. G. N. L. W. (2024). Klasifikasi Jenis Jerawat Berdasarkan Citra Menggunakan Convolutional Neural Network dengan Arsitektur MobileNetV2. Jurnal Fasilkom, 14(3), 766–774.
[7] Ramadhani, F., Rahardiantoro, S., & Masjkur, M. (2024). Acne Severity Classification Study Using CNN Algorithm with MobileNetV2 Architecture. Indonesian Journal of Statistics and Its Applications, 8(2), 112–128.
[8] Andini, A. R., & Yuadi, I. (2025). Classification of Acne Type Based on Convolutional Neural Network. MALCOM: Indonesian Journal of Machine Learning and Computer Science, 5(1), 301–308.
[9] Pramono, A. Y., & Kusnawi. (2025). Multi-Class Facial Acne Classification Using the EfficientNetV2-S Deep Learning Model. AVITEC Journal, 7(3), 299–309.
[10] Zhang, H., & Ma, X. (2022). Ensemble Network for Acne Detection and Severity Grading. IEEE Access, 10, 11425–11439.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Ahmad Khoirudin Affandi
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
