Performance Analysis of MobileNetV3-based Convolutional Neural Network for Facial Skin Disorder Classification

Herimanto; Arie Satia Dharma; Junita Amalia; David Largo; Christin Adelia Pratiwi Sihite

doi:10.29207/resti.v8i6.5982

Herimanto Institut Teknologi Del
Arie Satia Dharma Institut Teknologi Del
Junita Amalia Institut Teknologi Del
David Largo Institut Teknologi Del
Christin Adelia Pratiwi Sihite Institut Teknologi Del

DOI: https://doi.org/10.29207/resti.v8i6.5982

Keywords: CNN, Deep Learning, Mobilenetv3, Skin Classification

Abstract

Accurately identifying facial skin types is essential for recommending the right skincare treatments and products. Misidentifying skin types can lead to negative consequences, such as irritation or worsening of skin conditions. This study investigated methods for classifying facial skin types into five categories: oily, acne-prone, dry, normal, and combination. A dataset of 1725 augmented facial images was used. Data augmentation techniques likely increased the dataset's diversity, which helps improve the model's generalization ability. The data underwent preprocessing, including rescaling, before being applied to two deep learning models, CNN and MobileNetV3. The models were evaluated based on accuracy and execution time to determine the most effective approach for classifying facial skin types. The CNN model achieved an accuracy of 64%, demonstrating its potential for image classification tasks. However, the MobileNetV3 model significantly outperformed CNN with an accuracy of 84%. This superior performance is attributed to MobileNetV3's advanced architecture, which is optimized for efficient feature extraction, and particularly relevant for capturing the subtle variations in facial skin types. Therefore, MobileNetV3 emerged as the more effective method for classifying facial skin types with higher accuracy.

Downloads

Download data is not yet available.

References

M. Ath-Thariq and T. N. Suharsono, “Deteksi Penyakit Kulit Serupa Pada Wajah Berbasis Mobile dengan Metode Convolutional Neural Network,” vol. 3, no. 5, pp. 876–887, Oct. 2023, doi: https://doi.org/10.31004/innovative.v3i5.4936.

J. Zdrada, W. Odrzywołek, A. Stolecka‐Warzecha, S. Wilczyński, and B. Błońska‐Fajfrowska, “The influence of cosmetics dedicated to oily and acne‐prone skin on skin parameters,” J. Cosmet. Dermatol., vol. 21, no. 11, pp. 6092–6099, Nov. 2022, doi: 10.1111/jocd.15143.

M. A. Farage, “The Prevalence of Sensitive Skin,” Front. Med., vol. 6, p. 98, May 2019, doi: 10.3389/fmed.2019.00098.

S. D. Kusumaningrum and I. Muhimmah, “Analisis Faktor dan Metode untuk Menentukan Tipe Kulit Wajah: Tinjauan Literatur,” J. Teknol. Inf. Dan Ilmu Komput., vol. 10, no. 4, pp. 753–762, Aug. 2023, doi: 10.25126/jtiik.20241046955.

Dian Anisa Agustina, “KLASIFIKASI CITRA JENIS KULIT WAJAH DENGAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK (CNN) RESNET-50,” J. Ris. Sist. Inf., vol. 1, no. 3, pp. 01–07, Jul. 2024, doi: 10.69714/13sbby24.

J. Lalrengpuii, K. Raza, A. Mishra, and R. Shukla, “Retinoid nano particulates: Approachable gateway for acne treatment,” Health Sci. Rev., vol. 4, p. 100042, Sep. 2022, doi: 10.1016/j.hsr.2022.100042.

R. Oliveira, J. Ferreira, L. F. Azevedo, and I. F. Almeida, “An Overview of Methods to Characterize Skin Type: Focus on Visual Rating Scales and Self-Report Instruments,” Cosmetics, vol. 10, no. 1, p. 14, Jan. 2023, doi: 10.3390/cosmetics10010014.

R. J. Rumandan, R. Nuraini, N. Sadikin, and Y. Rahmanto, “Klasifikasi Citra Jenis Daun Berkhasiat Obat Menggunakan Algoritma Jaringan Syaraf Tiruan Extreme Learning Machine,” J. Comput. Syst. Inform. JoSYC, vol. 4, no. 1, pp. 145–154, Dec. 2022, doi: 10.47065/josyc.v4i1.2586.

A. Peryanto, A. Yudhana, and R. Umar, “Rancang Bangun Klasifikasi Citra Dengan Teknologi Deep Learning Berbasis Metode Convolutional Neural Network,” Format J. Ilm. Tek. Inform., vol. 8, no. 2, p. 138, Feb. 2020, doi: 10.22441/format.2019.v8.i2.007.

M. R. Efrian and U. Latifa, “IMAGE RECOGNITION BERBASIS CONVOLUTIONAL NEURAL NETWORK (CNN) UNTUK MENDETEKSI PENYAKIT KULIT PADA MANUSIA,” Power Elektron. J. Orang Elektro, vol. 11, no. 2, p. 276, Jul. 2022, doi: 10.30591/polektro.v12i1.3874.

S. Saidah, 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),” in Proceedings of the 1st International Conference on Electronics, Biomedical Engineering, and Health Informatics, vol. 746, Triwiyanto, H. A. Nugroho, A. Rizal, and W. Caesarendra, Eds., in Lecture Notes in Electrical Engineering, vol. 746. , Singapore: Springer Singapore, 2021, pp. 75–83. doi: 10.1007/978-981-33-6926-9_7.

N. Afarini and D. Hindarto, “OPTIMIZATION OF CNN + MOBILENETV3 FOR INSECT IDENTIFICATION: TOWARD HIGH ACCURACY,” J. Teknol. Inf. Univ. Lambung Mangkurat JTIULM, vol. 9, no. 1, pp. 21–28, May 2024, doi: 10.20527/jtiulm.v9i1.199.

X. Chu, B. Zhang, and R. Xu, “MoGA: Searching Beyond Mobilenetv3,” in ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain: IEEE, May 2020, pp. 4042–4046. doi: 10.1109/ICASSP40776.2020.9054428.

F. A. Hariz, I. N. Yulita, and I. Suryana, “Human Activity Recognition Berdasarkan Tangkapan Webcam Menggunakan Metode Convolutional Neural Network (CNN) Dengan Arsitektur MobileNet,” JITSI J. Ilm. Teknol. Sist. Inf., vol. 3, no. 4, pp. 103–115, Dec. 2022, doi: 10.30630/jitsi.3.4.97.

C.-I. Moon and O. Lee, “Skin Microstructure Segmentation and Aging Classification Using CNN-Based Models,” IEEE Access, vol. 10, pp. 4948–4956, 2022, doi: 10.1109/ACCESS.2021.3140031.

E. S. Budi, A. N. Chan, P. P. Alda, and Muh. Arif. F. Idris, “Optimasi Model Machine Learning untuk Klasifikasi dan Prediksi Citra Menggunakan Algoritma Convolutional Neural Network,” RESOLUSI Rekayasa Tek. Inform. Dan Inf., vol. 4, no. 5, p. 502−509, May 2024, doi: https://doi.org/10.30865/resolusi.v4i5.1892.

P. M. B. G. Maia Campos, M. O. Melo, and D. G. Mercurio, “Use of Advanced Imaging Techniques for the Characterization of Oily Skin,” Front. Physiol., vol. 10, p. 254, Mar. 2019, doi: 10.3389/fphys.2019.00254.

Y. D. Rosita and L. S. Moonlight, “Perbandingan Metode Prediksi untuk Nilai Jual USD: Holt-Winters, Holt’s, dan Single Exponential Smoothing,” JTIM J. Teknol. Inf. Dan Multimed., vol. 5, no. 4, pp. 322–333, Jan. 2024, doi: 10.35746/jtim.v5i4.473.

R. Kurniawan, P. B. Wintoro, Y. Mulyani, and M. Komarudin, “IMPLEMENTASI ARSITEKTUR XCEPTION PADA MODEL MACHINE LEARNING KLASIFIKASI SAMPAH ANORGANIK,” J. Inform. Dan Tek. Elektro Terap., vol. 11, no. 2, Apr. 2023, doi: 10.23960/jitet.v11i2.3034.

A. Rusdy Prasetyo, Sussi, and B. Aditya, “ANALISIS PERBANDINGAN ALGORITMA SUPPORT VECTOR MACHINE (SVM) DAN CONVOLUTIONAL NEURAL NETWORK (CNN) UNTUK SISTEM DETEKSI KATARAK,” J. Ilm. Tek. Mesin Elektro Dan Komput., vol. 3, no. 1, pp. 1–10, Mar. 2023, doi: 10.51903/juritek.v3i1.604.

R.-Y. Sun, “Optimization for Deep Learning: An Overview,” J. Oper. Res. Soc. China, vol. 8, no. 2, pp. 249–294, Jun. 2020, doi: 10.1007/s40305-020-00309-6.

R. Cobilla et al., “Classification of the Type of Brain Tumor in MRI Using Xception Model,” in 2023 International Conference on Electronics, Information, and Communication (ICEIC), Singapore: IEEE, Feb. 2023, pp. 1–4. doi: 10.1109/ICEIC57457.2023.10049979.

M. R. Alwanda, R. P. K. Ramadhan, and D. Alamsyah, “Implementasi Metode Convolutional Neural Network Menggunakan Arsitektur LeNet-5 untuk Pengenalan Doodle,” J. Algoritme, vol. 1, no. 1, pp. 45–56, Oct. 2020, doi: 10.35957/algoritme.v1i1.434.