Development of a Face Skin Type Classification System Based on CNN MobileNetV2 for Smartphones
DOI:
https://doi.org/10.33795/jartel.v14i2.6684Keywords:
Convolutional Neural Networks (CNN), Image Processing, MobileNetV2, Skin Classification, Smartphone ApplicationAbstract
This research aims to develop a Facial Skin Type Classification System using Convolutional Neural Networks (CNN) with the MobileNetV2 architecture implemented on Android-based smartphone devices. Facial skin is classified into four main categories: normal, combination, oily, and dry, based on characteristics such as moisture, oil production, and skin texture. CNN was chosen for its ability to accurately recognize image patterns, while MobileNetV2 is designed for low-spec devices, allowing the classification process to run quickly and efficiently. The deep learning method is used to classify facial skin types with optimal accuracy and computational efficiency. The facial skin image dataset was collected and trained using transfer learning on the MobileNetV2 model. The research process includes the collection of facial skin image datasets, preprocessing, model training, testing, and implementation in the application. The facial skin image dataset was collected and trained using transfer learning on the MobileNetV2 model. The results show that this system is capable of classifying skin types with high accuracy of 87.5% in an average computation time of 0.4 seconds at a distance of 15–20 cm under bright lighting conditions
References
M. R. Farhan, A. W. Widodo, and M. A. Rahman, "Ekstraksi Ciri Pada Klasifikasi Tipe Kulit Wajah Menggunakan Metode Haar Wavelet," J. Pengemb. Teknol. Inf. dan Ilmu Komput. , vol. 3, no. 3, pp. 2903–2909, 2019.
Z. Wang et al., "Deep Learning Approaches for Skin Type Classification," J. Mach. Learn. Healthcare , vol. 15, no. 3, pp. 245–260, 2022.
L. Chen and S. Kumar, "Mobile Machine Learning: Trends and Applications," in Int. Conf. Mob. Comput. , 2021, pp. 78–92.
M. Rodriguez et al., "Convolutional Neural Networks in Dermatological Image Analysis," IEEE Trans. Med. Imaging , vol. 39, no. 7, pp. 2235–2247, 2020.
M. Sandler et al., "MobileNetV2: Inverted Residuals and Linear Bottlenecks," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. , 2018, pp. 4510–4520.
F. Meiristika et al., "Detection of Facial Skin Type Classification Using CNN with MobileNet Architecture," J. Mach. Vis. , vol. 12, no. 2, pp. 123–130, 2022.
Hartanto et al., "Development of Mobile Skin Cancer Detection using Faster R-CNN and MobileNetV2 Model," Med. Imaging Innov. , vol. 8, no. 4, pp. 201–209, 2020.
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L. C. Chen, "MobileNetV2: Inverted Residuals and Linear Bottlenecks," in Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. , 2018, pp. 4510–4520.
A. Anton, N. F. Nissa, A. Janiati, N. Cahya, and P. Astuti, "Application of Deep Learning Using Convolutional Neural Network (CNN) Method for Women’s Skin Classification," Sci. J. Informatics, vol. 8, no. 1, pp. 144–153, 2021.
Keras, "About Keras," Keras, 2023. [Online]. Available: https://keras.io
G. C. Pinaria, Y. D. Rindengan, X. B. N. Najoan, T. Elektro, U. Sam, and J. K. B. Manado, "Web Based E-Commerce Application Buying and Selling Food Ingredients for Manado City," J. Tek. Inform. , pp. 1–8, 2021.
B. A. B. Ii, "Landasan Teori Visual Code," pp. 6–18, 2011.
R. Hermiati, Asnawati, and I. Kanedi, "Pembuatan E-Commerce Pada Raja Komputer Menggunakan Bahasa," J. Media Infotama , vol. 17, no. 1, pp. 54–66, 2021.
Arikunto, Prosedur Penelitian Suatu Pendekatan Praktek. Jakarta: PT. Rineka Cipta, 2006.
Sugiyono, Metode Penelitian Kuantitatif Kualitatif dan R&D. Bandung: ALFABETA, 2008.
J. Kim and H. Park, "Efficient Deep Learning Models for Mobile Platforms," J. Mob. Intell., vol. 11, no. 2, pp. 112–125, 2023.
