Analisis Perfoma Resnet-50 Dalam Identifikasi Jenis Kulit Wajah
DOI:
https://doi.org/10.29407/qxmg2629Abstract
Identifikasi jenis kulit wajah secara manual sering menghasilkan penilaian yang subjektif dan kurang konsisten. Penelitian ini bertujuan untuk menganalisis performa metode Convolutional Neural Network (CNN) dengan arsitektur ResNet-50 dalam mengidentifikasi jenis kulit wajah berdasarkan citra digital. Dataset yang digunakan terdiri dari empat kelas, yaitu normal, dry, oily, dan acne. Tahapan penelitian meliputi preprocessing data, augmentasi citra, pelatihan model, dan evaluasi menggunakan confusion matrix serta accuracy. Proses pelatihan dilakukan selama 20 epoch menggunakan optimizer SGD dan learning rate scheduler. Hasil penelitian menunjukkan bahwa model mengalami peningkatan performa yang baik selama proses training dengan nilai accuracy mencapai 90%. Selain itu, hasil confusion matrix menunjukkan bahwa sebagian besar data berhasil diklasifikasikan dengan benar pada setiap kelas, terutama pada kelas acne yang memperoleh hasil prediksi sempurna. Berdasarkan hasil tersebut, arsitektur ResNet-50 memiliki performa yang baik dan berpotensi digunakan sebagai sistem identifikasi jenis kulit wajah secara otomatis.
Keywords:
CNN, ResNet-50, Klasifikasi citra, jenis kulit wajah, deep learning.##plugins.themes.default.displayStats.downloads##
References
[1] N. H. Muttaqin and A. M. Widodo, “Evaluation of Transfer Learning-Based Convolutional
Neural Networks (InceptionV3 and MobileNetV2) for Facial Skin-Type Classification,”
Jurnal Ilmu Komputer dan Informatika, vol. 5, no. 1, pp. 11–32, Aug. 2025, doi:
10.54082/jiki.264.
[2] D. Marya, C. Mustika, S. Ramadhani, and R. Ardiansyah, “Development of an Optimized
Facial Skin Type Classification System using CNN MobileNetV2 for Real-Time
Smartphone Applications,” Journal of Telecommunication Network, vol. 15, no. 1, 2025.
[3] K. Sakti Santriantara et al., “JUTEKOM Jurnal Teknologi dan Ilmu Komputer DETEKSI
ACNE VULGARIS DAN JENIS KULIT PADA CITRA WAJAH BERBASIS YOLOV7
DAN RESNET50”, [Online]. Available: https://jurnal.nolsatu.co.id/jutekom
[4] Herimanto, A. S. Dharma, J. Amalia, D. Largo, and C. A. P. Sihite, “Performance Analysis
of MobileNetV3-based Convolutional Neural Network for Facial Skin Disorder
Classification,” Jurnal RESTI, vol. 8, no. 6, pp. 701–709, Dec. 2024, doi:
10.29207/resti.v8i6.5982.
[5] K. Sakti Santriantara et al., “JUTEKOM Jurnal Teknologi dan Ilmu Komputer DETEKSI
ACNE VULGARIS DAN JENIS KULIT PADA CITRA WAJAH BERBASIS YOLOV7
DAN RESNET50”, [Online]. Available: https://jurnal.nolsatu.co.id/jutekom
[6] N. I. Khani and S. Rakasiwi, “Penerapan Convolutional Neural Network dengan ResNet-
50 untuk Klasifikasi Penyakit Kulit Wajah Efektif,” Edumatic: Jurnal Pendidikan
Informatika, vol. 9, no. 1, pp. 217–225, Apr. 2025, doi: 10.29408/edumatic.v9i1.29572.
[7] M. Jiemesha and D. M. Wonohadidjojo, “Classification of Skin Diseases Using Transfer
Learning with ResNet-50 Architecture and Data Preprocessing Using Real-ESRGAN and
Wiener Filter,” Journal of Intelligent System and Computation, vol. 7, no. 1, pp. 01–10,
May 2025, doi: 10.52985/insyst.v7i1.399.
[8] N. I. Khani and S. Rakasiwi, “Penerapan Convolutional Neural Network dengan ResNet-
50 untuk Klasifikasi Penyakit Kulit Wajah Efektif,” Edumatic: Jurnal Pendidikan
Informatika, vol. 9, no. 1, pp. 217–225, Apr. 2025, doi: 10.29408/edumatic.v9i1.29572.
[9] J. Homepage, N. Nur Kumala, A. Muqtadir, and A. Arifia, “MALCOM: Indonesian Journal
of Machine Learning and Computer Science Performance Comparison of Facial Skin Type
Classification Using the Segment Anything Model,” vol. 6, no. 2, pp. 599–607, 2026, doi:
10.57152/malcom.v6i2.2604.
[10] S. Sa’idah, Y. N. Fuadah, F. Alia, N. Ibrahim, R. Magdalena, and S. Rizal, “Facial Skin
Type Classification Based on Microscopic Images using Convolutional Neural Network
(CNN).”
[11] G. P. H. P. Gusti, E. Haerani, F. Syafria, F. Yanto, and S. K. Gusti, “Implementasi Algoritma
Convolutional Neural Network (Resnet-50) untuk Klasifikasi Kanker Kulit Benign dan
Malignant,” MALCOM: Indonesian Journal of Machine Learning and Computer Science,
vol. 4, no. 3, pp. 984–992, Jun. 2024, doi: 10.57152/malcom.v4i3.1398.
[12] M. Fauzan Novriandy, B. Rahmat, and A. Junaidi, “KLASIFIKASI CITRA PENYAKIT
KANKER MULUT MENGGUNAKAN ARSITEKTUR RESNET50 OPTIMASI ADAM
DAN SGD,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 12, no. 3, Aug. 2024,
doi: 10.23960/jitet.v12i3.4732.
[13] Dian Anisa Agustina, “KLASIFIKASI CITRA JENIS KULIT WAJAH DENGAN
ALGORITMA CONVOLUTIONAL NEURAL NETWORK (CNN) RESNET-50,” Jurnal
Riset Sistem Informasi, vol. 1, no. 3, pp. 01–07, Jul. 2024, doi: 10.69714/13sbby24.
[14] J. Homepage, N. Nur Kumala, A. Muqtadir, and A. Arifia, “MALCOM: Indonesian Journal
of Machine Learning and Computer Science Performance Comparison of Facial Skin Type
Classification Using the Segment Anything Model,” vol. 6, no. 2, pp. 599–607, 2026, doi:
10.57152/malcom.v6i2.2604.
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
