Development of a Face Skin Type Classification System Based on CNN MobileNetV2 for Smartphones

Abstract

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